Merge branch 'main' into chore/remove-cursor-target-support

.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
     {
       "name": "compound-engineering",
       "description": "AI-powered development tools that get smarter with every use. Make each unit of engineering work easier than the last. Includes 29 specialized agents, 22 commands, and 19 skills.",
-      "version": "2.33.0",
+      "version": "2.34.0",
       "author": {
         "name": "Kieran Klaassen",
         "url": "https://github.com/kieranklaassen",

.gitignore

@@ -2,3 +2,4 @@
 *.log
 node_modules/
 .codex/
+todos/

README.md

@@ -18,9 +18,9 @@ A Claude Code plugin marketplace featuring the **Compound Engineering Plugin**
 /add-plugin compound-engineering
 ```
 
-## OpenCode, Codex, Droid & Pi (experimental) Install
+## OpenCode, Codex, Droid & Pi & Gemini (experimental) Install
 
-This repo includes a Bun/TypeScript CLI that converts Claude Code plugins to OpenCode, Codex, Factory Droid and Pi.
+This repo includes a Bun/TypeScript CLI that converts Claude Code plugins to OpenCode, Codex, Factory Droid, Pi, and Gemini CLI.
 
 ```bash
 # convert the compound-engineering plugin into OpenCode format
@@ -34,6 +34,9 @@ bunx @every-env/compound-plugin install compound-engineering --to droid
 
 # convert to Pi format
 bunx @every-env/compound-plugin install compound-engineering --to pi
+
+# convert to Gemini CLI format
+bunx @every-env/compound-plugin install compound-engineering --to gemini
 ```
 
 Local dev:
@@ -46,6 +49,7 @@ OpenCode output is written to `~/.config/opencode` by default, with `opencode.js
 Codex output is written to `~/.codex/prompts` and `~/.codex/skills`, with each Claude command converted into both a prompt and a skill (the prompt instructs Codex to load the corresponding skill). Generated Codex skill descriptions are truncated to 1024 characters (Codex limit).
 Droid output is written to `~/.factory/` with commands, droids (agents), and skills. Claude tool names are mapped to Factory equivalents (`Bash` → `Execute`, `Write` → `Create`, etc.) and namespace prefixes are stripped from commands.
 Pi output is written to `~/.pi/agent/` by default with prompts, skills, extensions, and `compound-engineering/mcporter.json` for MCPorter interoperability.
+Gemini output is written to `.gemini/` with skills (from agents), commands (`.toml`), and `settings.json` (MCP servers). Namespaced commands create directory structure (`workflows:plan` → `commands/workflows/plan.toml`). Skills use the identical SKILL.md standard and pass through unchanged.
 
 All provider targets are experimental and may change as the formats evolve.
 

docs/plans/2026-02-14-feat-add-gemini-cli-target-provider-plan.md

@@ -0,0 +1,370 @@
+---
+title: Add Gemini CLI as a Target Provider
+type: feat
+status: completed
+completed_date: 2026-02-14
+completed_by: "Claude Opus 4.6"
+actual_effort: "Completed in one session"
+date: 2026-02-14
+---
+
+# Add Gemini CLI as a Target Provider
+
+## Overview
+
+Add `gemini` as a sixth target provider in the converter CLI, alongside `opencode`, `codex`, `droid`, `cursor`, and `pi`. This enables `--to gemini` for both `convert` and `install` commands, converting Claude Code plugins into Gemini CLI-compatible format.
+
+Gemini CLI ([google-gemini/gemini-cli](https://github.com/google-gemini/gemini-cli)) is Google's open-source AI agent for the terminal. It supports GEMINI.md context files, custom commands (TOML format), agent skills (SKILL.md standard), MCP servers, and extensions -- making it a strong conversion target with good coverage of Claude Code plugin concepts.
+
+## Component Mapping
+
+| Claude Code | Gemini Equivalent | Notes |
+|---|---|---|
+| `agents/*.md` | `.gemini/skills/*/SKILL.md` | Agents become skills -- Gemini activates them on demand via `activate_skill` tool based on description matching |
+| `commands/*.md` | `.gemini/commands/*.toml` | TOML format with `prompt` and `description` fields; namespaced via directory structure |
+| `skills/*/SKILL.md` | `.gemini/skills/*/SKILL.md` | **Identical standard** -- copy directly |
+| MCP servers | `settings.json` `mcpServers` | Same MCP protocol; different config location (`settings.json` vs `.mcp.json`) |
+| `hooks/` | `settings.json` hooks | Gemini has hooks (`BeforeTool`, `AfterTool`, `SessionStart`, etc.) but different format; emit `console.warn` and skip for now |
+| `.claude/` paths | `.gemini/` paths | Content rewriting needed |
+
+### Key Design Decisions
+
+**1. Agents become skills (not GEMINI.md context)**
+
+With 29 agents, dumping them into GEMINI.md would flood every session's context. Instead, agents convert to skills -- Gemini autonomously activates them based on the skill description when relevant. This matches how Claude Code agents are invoked on demand via the Task tool.
+
+**2. Commands use TOML format with directory-based namespacing**
+
+Gemini CLI commands are `.toml` files where the path determines the command name: `.gemini/commands/git/commit.toml` becomes `/git:commit`. This maps cleanly from Claude Code's colon-namespaced commands (`workflows:plan` -> `.gemini/commands/workflows/plan.toml`).
+
+**3. Commands use `{{args}}` placeholder**
+
+Gemini's TOML commands support `{{args}}` for argument injection, mapping from Claude Code's `argument-hint` field. Commands with `argument-hint` get `{{args}}` appended to the prompt.
+
+**4. MCP servers go into project-level settings.json**
+
+Gemini CLI reads MCP config from `.gemini/settings.json` under the `mcpServers` key. The format is compatible -- same `command`, `args`, `env` fields, plus Gemini-specific `cwd`, `timeout`, `trust`, `includeTools`, `excludeTools`.
+
+**5. Skills pass through unchanged**
+
+Gemini adopted the same SKILL.md standard (YAML frontmatter with `name` and `description`, markdown body). Skills copy directly.
+
+### TOML Command Format
+
+```toml
+description = "Brief description of the command"
+prompt = """
+The prompt content that will be sent to Gemini.
+
+User request: {{args}}
+"""
+```
+
+- `description` (string): One-line description shown in `/help`
+- `prompt` (string): The prompt sent to the model; supports `{{args}}`, `!{shell}`, `@{file}` placeholders
+
+### Skill (SKILL.md) Format
+
+```yaml
+---
+name: skill-name
+description: When and how Gemini should use this skill
+---
+
+# Skill Title
+
+Detailed instructions...
+```
+
+Identical to Claude Code's format. The `description` field is critical -- Gemini uses it to decide when to activate the skill.
+
+### MCP Server Format (settings.json)
+
+```json
+{
+  "mcpServers": {
+    "server-name": {
+      "command": "npx",
+      "args": ["-y", "package-name"],
+      "env": { "KEY": "value" }
+    }
+  }
+}
+```
+
+## Acceptance Criteria
+
+- [x] `bun run src/index.ts convert --to gemini ./plugins/compound-engineering` produces valid Gemini config
+- [x] Agents convert to `.gemini/skills/*/SKILL.md` with populated `description` in frontmatter
+- [x] Commands convert to `.gemini/commands/*.toml` with `prompt` and `description` fields
+- [x] Namespaced commands create directory structure (`workflows:plan` -> `commands/workflows/plan.toml`)
+- [x] Commands with `argument-hint` include `{{args}}` placeholder in prompt
+- [x] Commands with `disable-model-invocation: true` are still included (TOML commands are prompts, not code)
+- [x] Skills copied to `.gemini/skills/` (identical format)
+- [x] MCP servers written to `.gemini/settings.json` under `mcpServers` key
+- [x] Existing `.gemini/settings.json` is backed up before overwrite, and MCP config is merged (not clobbered)
+- [x] Content transformation rewrites `.claude/` and `~/.claude/` paths to `.gemini/` and `~/.gemini/`
+- [x] `/workflows:plan` transformed to `/workflows:plan` (Gemini preserves colon namespacing via directories)
+- [x] `Task agent-name(args)` transformed to `Use the agent-name skill to: args`
+- [x] Plugins with hooks emit `console.warn` about format differences
+- [x] Writer does not double-nest `.gemini/.gemini/`
+- [x] `model` and `allowedTools` fields silently dropped (no Gemini equivalent in skills/commands)
+- [x] Converter and writer tests pass
+- [x] Existing tests still pass (`bun test`)
+
+## Implementation
+
+### Phase 1: Types
+
+**Create `src/types/gemini.ts`**
+
+```typescript
+export type GeminiSkill = {
+  name: string
+  content: string // Full SKILL.md with YAML frontmatter
+}
+
+export type GeminiSkillDir = {
+  name: string
+  sourceDir: string
+}
+
+export type GeminiCommand = {
+  name: string       // e.g. "plan" or "workflows/plan"
+  content: string    // Full TOML content
+}
+
+export type GeminiBundle = {
+  generatedSkills: GeminiSkill[]     // From agents
+  skillDirs: GeminiSkillDir[]         // From skills (pass-through)
+  commands: GeminiCommand[]
+  mcpServers?: Record<string, {
+    command?: string
+    args?: string[]
+    env?: Record<string, string>
+    url?: string
+    headers?: Record<string, string>
+  }>
+}
+```
+
+### Phase 2: Converter
+
+**Create `src/converters/claude-to-gemini.ts`**
+
+Core functions:
+
+1. **`convertClaudeToGemini(plugin, options)`** -- main entry point
+   - Convert each agent to a skill via `convertAgentToSkill()`
+   - Convert each command via `convertCommand()`
+   - Pass skills through as directory references
+   - Convert MCP servers to settings-compatible object
+   - Emit `console.warn` if `plugin.hooks` has entries
+
+2. **`convertAgentToSkill(agent)`** -- agent -> SKILL.md
+   - Frontmatter: `name` (from agent name), `description` (from agent description, max ~300 chars)
+   - Body: agent body with content transformations applied
+   - Prepend capabilities section if present
+   - Silently drop `model` field (no Gemini equivalent)
+   - If description is empty, generate from agent name: `"Use this skill for ${agent.name} tasks"`
+
+3. **`convertCommand(command, usedNames)`** -- command -> TOML file
+   - Preserve namespace structure: `workflows:plan` -> path `workflows/plan`
+   - `description` field from command description
+   - `prompt` field from command body with content transformations
+   - If command has `argument-hint`, append `\n\nUser request: {{args}}` to prompt
+   - Body: apply `transformContentForGemini()` transformations
+   - Silently drop `allowedTools` (no Gemini equivalent)
+
+4. **`transformContentForGemini(body)`** -- content rewriting
+   - `.claude/` -> `.gemini/` and `~/.claude/` -> `~/.gemini/`
+   - `Task agent-name(args)` -> `Use the agent-name skill to: args`
+   - `@agent-name` references -> `the agent-name skill`
+   - Skip file paths (containing `/`) and common non-command patterns
+
+5. **`convertMcpServers(servers)`** -- MCP config
+   - Map each `ClaudeMcpServer` entry to Gemini-compatible JSON
+   - Pass through: `command`, `args`, `env`, `url`, `headers`
+   - Drop `type` field (Gemini infers transport)
+
+6. **`toToml(description, prompt)`** -- TOML serializer
+   - Escape TOML strings properly
+   - Use multi-line strings (`"""`) for prompt field
+   - Simple string for description
+
+### Phase 3: Writer
+
+**Create `src/targets/gemini.ts`**
+
+Output structure:
+
+```
+.gemini/
+├── commands/
+│   ├── plan.toml
+│   └── workflows/
+│       └── plan.toml
+├── skills/
+│   ├── agent-name-1/
+│   │   └── SKILL.md
+│   ├── agent-name-2/
+│   │   └── SKILL.md
+│   └── original-skill/
+│       └── SKILL.md
+└── settings.json          (only mcpServers key)
+```
+
+Core function: `writeGeminiBundle(outputRoot, bundle)`
+
+- `resolveGeminiPaths(outputRoot)` -- detect if path already ends in `.gemini` to avoid double-nesting (follow droid writer pattern)
+- Write generated skills to `skills/<name>/SKILL.md`
+- Copy original skill directories to `skills/` via `copyDir()`
+- Write commands to `commands/` as `.toml` files, creating subdirectories for namespaced commands
+- Write `settings.json` with `{ "mcpServers": {...} }` via `writeJson()` with `backupFile()` for existing files
+- If settings.json exists, read it first and merge `mcpServers` key (don't clobber other settings)
+
+### Phase 4: Wire into CLI
+
+**Modify `src/targets/index.ts`**
+
+```typescript
+import { convertClaudeToGemini } from "../converters/claude-to-gemini"
+import { writeGeminiBundle } from "./gemini"
+import type { GeminiBundle } from "../types/gemini"
+
+// Add to targets:
+gemini: {
+  name: "gemini",
+  implemented: true,
+  convert: convertClaudeToGemini as TargetHandler<GeminiBundle>["convert"],
+  write: writeGeminiBundle as TargetHandler<GeminiBundle>["write"],
+},
+```
+
+**Modify `src/commands/convert.ts`**
+
+- Update `--to` description: `"Target format (opencode | codex | droid | cursor | pi | gemini)"`
+- Add to `resolveTargetOutputRoot`: `if (targetName === "gemini") return path.join(outputRoot, ".gemini")`
+
+**Modify `src/commands/install.ts`**
+
+- Same two changes as convert.ts
+
+### Phase 5: Tests
+
+**Create `tests/gemini-converter.test.ts`**
+
+Test cases (use inline `ClaudePlugin` fixtures, following existing converter test patterns):
+
+- Agent converts to skill with SKILL.md frontmatter (`name` and `description` populated)
+- Agent with empty description gets default description text
+- Agent with capabilities prepended to body
+- Agent `model` field silently dropped
+- Agent with empty body gets default body text
+- Command converts to TOML with `prompt` and `description` fields
+- Namespaced command creates correct path (`workflows:plan` -> `workflows/plan`)
+- Command with `disable-model-invocation` is still included
+- Command `allowedTools` silently dropped
+- Command with `argument-hint` gets `{{args}}` placeholder in prompt
+- Skills pass through as directory references
+- MCP servers convert to settings.json-compatible config
+- Content transformation: `.claude/` paths -> `.gemini/`
+- Content transformation: `~/.claude/` paths -> `~/.gemini/`
+- Content transformation: `Task agent(args)` -> natural language skill reference
+- Hooks present -> `console.warn` emitted
+- Plugin with zero agents produces empty generatedSkills array
+- Plugin with only skills works correctly
+- TOML output is valid (description and prompt properly escaped)
+
+**Create `tests/gemini-writer.test.ts`**
+
+Test cases (use temp directories, following existing writer test patterns):
+
+- Full bundle writes skills, commands, settings.json
+- Generated skills written as `skills/<name>/SKILL.md`
+- Original skills copied to `skills/` directory
+- Commands written as `.toml` files in `commands/` directory
+- Namespaced commands create subdirectories (`commands/workflows/plan.toml`)
+- MCP config written as valid JSON `settings.json` with `mcpServers` key
+- Existing `settings.json` is backed up before overwrite
+- Output root already ending in `.gemini` does NOT double-nest
+- Empty bundle produces no output
+
+### Phase 6: Documentation
+
+**Create `docs/specs/gemini.md`**
+
+Document the Gemini CLI spec as reference, following existing `docs/specs/codex.md` pattern:
+
+- GEMINI.md context file format
+- Custom commands format (TOML with `prompt`, `description`)
+- Skills format (identical SKILL.md standard)
+- MCP server configuration (`settings.json`)
+- Extensions system (for reference, not converted)
+- Hooks system (for reference, format differences noted)
+- Config file locations (user-level `~/.gemini/` vs project-level `.gemini/`)
+- Directory layout conventions
+
+**Update `README.md`**
+
+Add `gemini` to the supported targets in the CLI usage section.
+
+## What We're NOT Doing
+
+- Not converting hooks (Gemini has hooks but different format -- `BeforeTool`/`AfterTool` with matchers -- warn and skip)
+- Not generating full `settings.json` (only `mcpServers` key -- user-specific settings like `model`, `tools.sandbox` are out of scope)
+- Not creating extensions (extension format is for distributing packages, not for converted plugins)
+- Not using `@{file}` or `!{shell}` placeholders in converted commands (would require analyzing command intent)
+- Not transforming content inside copied SKILL.md files (known limitation -- skills may reference `.claude/` paths internally)
+- Not clearing old output before writing (matches existing target behavior)
+- Not merging into existing settings.json intelligently beyond `mcpServers` key (too risky to modify user config)
+
+## Complexity Assessment
+
+This is a **medium change**. The converter architecture is well-established with five existing targets, so this is mostly pattern-following. The key novelties are:
+
+1. The TOML command format (unique among all targets -- need simple TOML serializer)
+2. Agents map to skills rather than a direct 1:1 concept (but this is the same pattern as codex)
+3. Namespaced commands use directory structure (new approach vs flattening in cursor/codex)
+4. MCP config goes into a broader `settings.json` file (need to merge, not clobber)
+
+Skills being identical across platforms simplifies things significantly. The TOML serialization is simple (only two fields: `description` string and `prompt` multi-line string).
+
+## References
+
+- [Gemini CLI Repository](https://github.com/google-gemini/gemini-cli)
+- [Gemini CLI Configuration](https://geminicli.com/docs/get-started/configuration/)
+- [Custom Commands (TOML)](https://geminicli.com/docs/cli/custom-commands/)
+- [Agent Skills](https://geminicli.com/docs/cli/skills/)
+- [Creating Skills](https://geminicli.com/docs/cli/creating-skills/)
+- [Extensions](https://geminicli.com/docs/extensions/writing-extensions/)
+- [MCP Servers](https://google-gemini.github.io/gemini-cli/docs/tools/mcp-server.html)
+- Existing cursor plan: `docs/plans/2026-02-12-feat-add-cursor-cli-target-provider-plan.md`
+- Existing codex converter: `src/converters/claude-to-codex.ts` (has `uniqueName()` and skill generation patterns)
+- Existing droid writer: `src/targets/droid.ts` (has double-nesting guard pattern)
+- Target registry: `src/targets/index.ts`
+
+## Completion Summary
+
+### What Was Delivered
+- [x] Phase 1: Types (`src/types/gemini.ts`)
+- [x] Phase 2: Converter (`src/converters/claude-to-gemini.ts`)
+- [x] Phase 3: Writer (`src/targets/gemini.ts`)
+- [x] Phase 4: CLI wiring (`src/targets/index.ts`, `src/commands/convert.ts`, `src/commands/install.ts`)
+- [x] Phase 5: Tests (`tests/gemini-converter.test.ts`, `tests/gemini-writer.test.ts`)
+- [x] Phase 6: Documentation (`docs/specs/gemini.md`, `README.md`)
+
+### Implementation Statistics
+- 10 files changed
+- 27 new tests added (129 total, all passing)
+- 148 output files generated from compound-engineering plugin conversion
+- 0 dependencies added
+
+### Git Commits
+- `201ad6d` feat(gemini): add Gemini CLI as sixth target provider
+- `8351851` docs: add Gemini CLI spec and update README with gemini target
+
+### Completion Details
+- **Completed By:** Claude Opus 4.6
+- **Date:** 2026-02-14
+- **Session:** Single session

docs/specs/gemini.md

@@ -0,0 +1,122 @@
+# Gemini CLI Spec (GEMINI.md, Commands, Skills, MCP, Settings)
+
+Last verified: 2026-02-14
+
+## Primary sources
+
+```
+https://github.com/google-gemini/gemini-cli
+https://geminicli.com/docs/get-started/configuration/
+https://geminicli.com/docs/cli/custom-commands/
+https://geminicli.com/docs/cli/skills/
+https://geminicli.com/docs/cli/creating-skills/
+https://geminicli.com/docs/extensions/writing-extensions/
+https://google-gemini.github.io/gemini-cli/docs/tools/mcp-server.html
+```
+
+## Config locations
+
+- User-level config: `~/.gemini/settings.json`
+- Project-level config: `.gemini/settings.json`
+- Project-level takes precedence over user-level for most settings.
+- GEMINI.md context file lives at project root (similar to CLAUDE.md).
+
+## GEMINI.md context file
+
+- A markdown file at project root loaded into every session's context.
+- Used for project-wide instructions, coding standards, and conventions.
+- Equivalent to Claude Code's CLAUDE.md.
+
+## Custom commands (TOML format)
+
+- Custom commands are TOML files stored in `.gemini/commands/`.
+- Command name is derived from the file path: `.gemini/commands/git/commit.toml` becomes `/git:commit`.
+- Directory-based namespacing: subdirectories create namespaced commands.
+- Each command file has two fields:
+  - `description` (string): One-line description shown in `/help`
+  - `prompt` (string): The prompt sent to the model
+- Supports placeholders:
+  - `{{args}}` — user-provided arguments
+  - `!{shell}` — output of a shell command
+  - `@{file}` — contents of a file
+- Example:
+
+```toml
+description = "Create a git commit with a good message"
+prompt = """
+Look at the current git diff and create a commit with a descriptive message.
+
+User request: {{args}}
+"""
+```
+
+## Skills (SKILL.md standard)
+
+- A skill is a folder containing `SKILL.md` plus optional supporting files.
+- Skills live in `.gemini/skills/`.
+- `SKILL.md` uses YAML frontmatter with `name` and `description` fields.
+- Gemini activates skills on demand via `activate_skill` tool based on description matching.
+- The `description` field is critical — Gemini uses it to decide when to activate the skill.
+- Format is identical to Claude Code's SKILL.md standard.
+- Example:
+
+```yaml
+---
+name: security-reviewer
+description: Review code for security vulnerabilities and OWASP compliance
+---
+
+# Security Reviewer
+
+Detailed instructions for security review...
+```
+
+## MCP server configuration
+
+- MCP servers are configured in `settings.json` under the `mcpServers` key.
+- Same MCP protocol as Claude Code; different config location.
+- Supports `command`, `args`, `env` for stdio transport.
+- Supports `url`, `headers` for HTTP/SSE transport.
+- Additional Gemini-specific fields: `cwd`, `timeout`, `trust`, `includeTools`, `excludeTools`.
+- Example:
+
+```json
+{
+  "mcpServers": {
+    "context7": {
+      "url": "https://mcp.context7.com/mcp"
+    },
+    "playwright": {
+      "command": "npx",
+      "args": ["-y", "@anthropic/mcp-playwright"]
+    }
+  }
+}
+```
+
+## Hooks
+
+- Gemini supports hooks: `BeforeTool`, `AfterTool`, `SessionStart`, etc.
+- Hooks use a different format from Claude Code hooks (matchers-based).
+- Not converted by the plugin converter — a warning is emitted.
+
+## Extensions
+
+- Extensions are distributable packages for Gemini CLI.
+- They extend functionality with custom tools, hooks, and commands.
+- Not used for plugin conversion (different purpose from Claude Code plugins).
+
+## Settings.json structure
+
+```json
+{
+  "model": "gemini-2.5-pro",
+  "mcpServers": { ... },
+  "tools": {
+    "sandbox": true
+  }
+}
+```
+
+- Only the `mcpServers` key is written during plugin conversion.
+- Other settings (model, tools, sandbox) are user-specific and out of scope.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@every-env/compound-plugin",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "type": "module",
   "private": false,
   "bin": {

plugins/compound-engineering/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "compound-engineering",
-  "version": "2.33.0",
+  "version": "2.34.0",
   "description": "AI-powered development tools. 29 agents, 22 commands, 19 skills, 1 MCP server for code review, research, design, and workflow automation.",
   "author": {
     "name": "Kieran Klaassen",

plugins/compound-engineering/CHANGELOG.md

@@ -5,6 +5,23 @@ All notable changes to the compound-engineering plugin will be documented in thi
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.34.0] - 2026-02-14
+
+### Added
+
+- **Gemini CLI target** — New converter target for [Gemini CLI](https://github.com/google-gemini/gemini-cli). Install with `--to gemini` to convert agents to `.gemini/skills/*/SKILL.md`, commands to `.gemini/commands/*.toml` (TOML format with `description` + `prompt`), and MCP servers to `.gemini/settings.json`. Skills pass through unchanged (identical SKILL.md standard). Namespaced commands create directory structure (`workflows:plan` → `commands/workflows/plan.toml`). 29 new tests. ([#190](https://github.com/EveryInc/compound-engineering-plugin/pull/190))
+
+---
+
+## [2.33.1] - 2026-02-13
+
+### Changed
+
+- **`/workflows:plan` command** - All plan templates now include `status: active` in YAML frontmatter. Plans are created with `status: active` and marked `status: completed` when work finishes.
+- **`/workflows:work` command** - Phase 4 now updates plan frontmatter from `status: active` to `status: completed` after shipping. Agents can grep for status to distinguish current vs historical plans.
+
+---
+
 ## [2.33.0] - 2026-02-12
 
 ### Added

plugins/compound-engineering/commands/workflows/plan.md

@@ -178,6 +178,7 @@ Select how comprehensive you want the issue to be, simpler is mostly better.
 ---
 title: [Issue Title]
 type: [feat|fix|refactor]
+status: active
 date: YYYY-MM-DD
 ---
 
@@ -230,6 +231,7 @@ end
 ---
 title: [Issue Title]
 type: [feat|fix|refactor]
+status: active
 date: YYYY-MM-DD
 ---
 
@@ -294,6 +296,7 @@ date: YYYY-MM-DD
 ---
 title: [Issue Title]
 type: [feat|fix|refactor]
+status: active
 date: YYYY-MM-DD
 ---
 

plugins/compound-engineering/commands/workflows/work.md

@@ -297,7 +297,14 @@ This command takes a work document (plan, specification, or todo file) and execu
    )"
    ```
 
-4. **Notify User**
+4. **Update Plan Status**
+
+   If the input document has YAML frontmatter with a `status` field, update it to `completed`:
+   ```
+   status: active  →  status: completed
+   ```
+
+5. **Notify User**
    - Summarize what was completed
    - Link to PR
    - Note any follow-up work needed

src/commands/convert.ts

@@ -23,7 +23,7 @@ export default defineCommand({
     to: {
       type: "string",
       default: "opencode",
-      description: "Target format (opencode | codex | droid | cursor | pi)",
+      description: "Target format (opencode | codex | droid | cursor | pi | gemini)",
     },
     output: {
       type: "string",
@@ -145,5 +145,6 @@ function resolveTargetOutputRoot(targetName: string, outputRoot: string, codexHo
   if (targetName === "pi") return piHome
   if (targetName === "droid") return path.join(os.homedir(), ".factory")
   if (targetName === "cursor") return path.join(outputRoot, ".cursor")
+  if (targetName === "gemini") return path.join(outputRoot, ".gemini")
   return outputRoot
 }

src/commands/install.ts

@@ -25,7 +25,7 @@ export default defineCommand({
     to: {
       type: "string",
       default: "opencode",
-      description: "Target format (opencode | codex | droid | cursor | pi)",
+      description: "Target format (opencode | codex | droid | cursor | pi | gemini)",
     },
     output: {
       type: "string",
@@ -183,6 +183,10 @@ function resolveTargetOutputRoot(
     const base = hasExplicitOutput ? outputRoot : process.cwd()
     return path.join(base, ".cursor")
   }
+  if (targetName === "gemini") {
+    const base = hasExplicitOutput ? outputRoot : process.cwd()
+    return path.join(base, ".gemini")
+  }
   return outputRoot
 }
 

src/converters/claude-to-gemini.ts

@@ -0,0 +1,193 @@
+import { formatFrontmatter } from "../utils/frontmatter"
+import type { ClaudeAgent, ClaudeCommand, ClaudeMcpServer, ClaudePlugin } from "../types/claude"
+import type { GeminiBundle, GeminiCommand, GeminiMcpServer, GeminiSkill } from "../types/gemini"
+import type { ClaudeToOpenCodeOptions } from "./claude-to-opencode"
+
+export type ClaudeToGeminiOptions = ClaudeToOpenCodeOptions
+
+const GEMINI_DESCRIPTION_MAX_LENGTH = 1024
+
+export function convertClaudeToGemini(
+  plugin: ClaudePlugin,
+  _options: ClaudeToGeminiOptions,
+): GeminiBundle {
+  const usedSkillNames = new Set<string>()
+  const usedCommandNames = new Set<string>()
+
+  const skillDirs = plugin.skills.map((skill) => ({
+    name: skill.name,
+    sourceDir: skill.sourceDir,
+  }))
+
+  // Reserve skill names from pass-through skills
+  for (const skill of skillDirs) {
+    usedSkillNames.add(normalizeName(skill.name))
+  }
+
+  const generatedSkills = plugin.agents.map((agent) => convertAgentToSkill(agent, usedSkillNames))
+
+  const commands = plugin.commands.map((command) => convertCommand(command, usedCommandNames))
+
+  const mcpServers = convertMcpServers(plugin.mcpServers)
+
+  if (plugin.hooks && Object.keys(plugin.hooks.hooks).length > 0) {
+    console.warn("Warning: Gemini CLI hooks use a different format (BeforeTool/AfterTool with matchers). Hooks were skipped during conversion.")
+  }
+
+  return { generatedSkills, skillDirs, commands, mcpServers }
+}
+
+function convertAgentToSkill(agent: ClaudeAgent, usedNames: Set<string>): GeminiSkill {
+  const name = uniqueName(normalizeName(agent.name), usedNames)
+  const description = sanitizeDescription(
+    agent.description ?? `Use this skill for ${agent.name} tasks`,
+  )
+
+  const frontmatter: Record<string, unknown> = { name, description }
+
+  let body = transformContentForGemini(agent.body.trim())
+  if (agent.capabilities && agent.capabilities.length > 0) {
+    const capabilities = agent.capabilities.map((c) => `- ${c}`).join("\n")
+    body = `## Capabilities\n${capabilities}\n\n${body}`.trim()
+  }
+  if (body.length === 0) {
+    body = `Instructions converted from the ${agent.name} agent.`
+  }
+
+  const content = formatFrontmatter(frontmatter, body)
+  return { name, content }
+}
+
+function convertCommand(command: ClaudeCommand, usedNames: Set<string>): GeminiCommand {
+  // Preserve namespace structure: workflows:plan -> workflows/plan
+  const commandPath = resolveCommandPath(command.name)
+  const pathKey = commandPath.join("/")
+  uniqueName(pathKey, usedNames) // Track for dedup
+
+  const description = command.description ?? `Converted from Claude command ${command.name}`
+  const transformedBody = transformContentForGemini(command.body.trim())
+
+  let prompt = transformedBody
+  if (command.argumentHint) {
+    prompt += `\n\nUser request: {{args}}`
+  }
+
+  const content = toToml(description, prompt)
+  return { name: pathKey, content }
+}
+
+/**
+ * Transform Claude Code content to Gemini-compatible content.
+ *
+ * 1. Task agent calls: Task agent-name(args) -> Use the agent-name skill to: args
+ * 2. Path rewriting: .claude/ -> .gemini/, ~/.claude/ -> ~/.gemini/
+ * 3. Agent references: @agent-name -> the agent-name skill
+ */
+export function transformContentForGemini(body: string): string {
+  let result = body
+
+  // 1. Transform Task agent calls
+  const taskPattern = /^(\s*-?\s*)Task\s+([a-z][a-z0-9-]*)\(([^)]+)\)/gm
+  result = result.replace(taskPattern, (_match, prefix: string, agentName: string, args: string) => {
+    const skillName = normalizeName(agentName)
+    return `${prefix}Use the ${skillName} skill to: ${args.trim()}`
+  })
+
+  // 2. Rewrite .claude/ paths to .gemini/
+  result = result
+    .replace(/~\/\.claude\//g, "~/.gemini/")
+    .replace(/\.claude\//g, ".gemini/")
+
+  // 3. Transform @agent-name references
+  const agentRefPattern = /@([a-z][a-z0-9-]*-(?:agent|reviewer|researcher|analyst|specialist|oracle|sentinel|guardian|strategist))/gi
+  result = result.replace(agentRefPattern, (_match, agentName: string) => {
+    return `the ${normalizeName(agentName)} skill`
+  })
+
+  return result
+}
+
+function convertMcpServers(
+  servers?: Record<string, ClaudeMcpServer>,
+): Record<string, GeminiMcpServer> | undefined {
+  if (!servers || Object.keys(servers).length === 0) return undefined
+
+  const result: Record<string, GeminiMcpServer> = {}
+  for (const [name, server] of Object.entries(servers)) {
+    const entry: GeminiMcpServer = {}
+    if (server.command) {
+      entry.command = server.command
+      if (server.args && server.args.length > 0) entry.args = server.args
+      if (server.env && Object.keys(server.env).length > 0) entry.env = server.env
+    } else if (server.url) {
+      entry.url = server.url
+      if (server.headers && Object.keys(server.headers).length > 0) entry.headers = server.headers
+    }
+    result[name] = entry
+  }
+  return result
+}
+
+/**
+ * Resolve command name to path segments.
+ * workflows:plan -> ["workflows", "plan"]
+ * plan -> ["plan"]
+ */
+function resolveCommandPath(name: string): string[] {
+  return name.split(":").map((segment) => normalizeName(segment))
+}
+
+/**
+ * Serialize to TOML command format.
+ * Uses multi-line strings (""") for prompt field.
+ */
+export function toToml(description: string, prompt: string): string {
+  const lines: string[] = []
+  lines.push(`description = ${formatTomlString(description)}`)
+
+  // Use multi-line string for prompt
+  const escapedPrompt = prompt.replace(/\\/g, "\\\\").replace(/"""/g, '\\"\\"\\"')
+  lines.push(`prompt = """`)
+  lines.push(escapedPrompt)
+  lines.push(`"""`)
+
+  return lines.join("\n")
+}
+
+function formatTomlString(value: string): string {
+  return JSON.stringify(value)
+}
+
+function normalizeName(value: string): string {
+  const trimmed = value.trim()
+  if (!trimmed) return "item"
+  const normalized = trimmed
+    .toLowerCase()
+    .replace(/[\\/]+/g, "-")
+    .replace(/[:\s]+/g, "-")
+    .replace(/[^a-z0-9_-]+/g, "-")
+    .replace(/-+/g, "-")
+    .replace(/^-+|-+$/g, "")
+  return normalized || "item"
+}
+
+function sanitizeDescription(value: string, maxLength = GEMINI_DESCRIPTION_MAX_LENGTH): string {
+  const normalized = value.replace(/\s+/g, " ").trim()
+  if (normalized.length <= maxLength) return normalized
+  const ellipsis = "..."
+  return normalized.slice(0, Math.max(0, maxLength - ellipsis.length)).trimEnd() + ellipsis
+}
+
+function uniqueName(base: string, used: Set<string>): string {
+  if (!used.has(base)) {
+    used.add(base)
+    return base
+  }
+  let index = 2
+  while (used.has(`${base}-${index}`)) {
+    index += 1
+  }
+  const name = `${base}-${index}`
+  used.add(name)
+  return name
+}

src/targets/gemini.ts

@@ -0,0 +1,68 @@
+import path from "path"
+import { backupFile, copyDir, ensureDir, pathExists, readJson, writeJson, writeText } from "../utils/files"
+import type { GeminiBundle } from "../types/gemini"
+
+export async function writeGeminiBundle(outputRoot: string, bundle: GeminiBundle): Promise<void> {
+  const paths = resolveGeminiPaths(outputRoot)
+  await ensureDir(paths.geminiDir)
+
+  if (bundle.generatedSkills.length > 0) {
+    for (const skill of bundle.generatedSkills) {
+      await writeText(path.join(paths.skillsDir, skill.name, "SKILL.md"), skill.content + "\n")
+    }
+  }
+
+  if (bundle.skillDirs.length > 0) {
+    for (const skill of bundle.skillDirs) {
+      await copyDir(skill.sourceDir, path.join(paths.skillsDir, skill.name))
+    }
+  }
+
+  if (bundle.commands.length > 0) {
+    for (const command of bundle.commands) {
+      await writeText(path.join(paths.commandsDir, `${command.name}.toml`), command.content + "\n")
+    }
+  }
+
+  if (bundle.mcpServers && Object.keys(bundle.mcpServers).length > 0) {
+    const settingsPath = path.join(paths.geminiDir, "settings.json")
+    const backupPath = await backupFile(settingsPath)
+    if (backupPath) {
+      console.log(`Backed up existing settings.json to ${backupPath}`)
+    }
+
+    // Merge mcpServers into existing settings if present
+    let existingSettings: Record<string, unknown> = {}
+    if (await pathExists(settingsPath)) {
+      try {
+        existingSettings = await readJson<Record<string, unknown>>(settingsPath)
+      } catch {
+        console.warn("Warning: existing settings.json could not be parsed and will be replaced.")
+      }
+    }
+
+    const existingMcp = (existingSettings.mcpServers && typeof existingSettings.mcpServers === "object")
+      ? existingSettings.mcpServers as Record<string, unknown>
+      : {}
+    const merged = { ...existingSettings, mcpServers: { ...existingMcp, ...bundle.mcpServers } }
+    await writeJson(settingsPath, merged)
+  }
+}
+
+function resolveGeminiPaths(outputRoot: string) {
+  const base = path.basename(outputRoot)
+  // If already pointing at .gemini, write directly into it
+  if (base === ".gemini") {
+    return {
+      geminiDir: outputRoot,
+      skillsDir: path.join(outputRoot, "skills"),
+      commandsDir: path.join(outputRoot, "commands"),
+    }
+  }
+  // Otherwise nest under .gemini
+  return {
+    geminiDir: path.join(outputRoot, ".gemini"),
+    skillsDir: path.join(outputRoot, ".gemini", "skills"),
+    commandsDir: path.join(outputRoot, ".gemini", "commands"),
+  }
+}

src/targets/index.ts

@@ -4,16 +4,19 @@ import type { CodexBundle } from "../types/codex"
 import type { DroidBundle } from "../types/droid"
 import type { CursorBundle } from "../types/cursor"
 import type { PiBundle } from "../types/pi"
+import type { GeminiBundle } from "../types/gemini"
 import { convertClaudeToOpenCode, type ClaudeToOpenCodeOptions } from "../converters/claude-to-opencode"
 import { convertClaudeToCodex } from "../converters/claude-to-codex"
 import { convertClaudeToDroid } from "../converters/claude-to-droid"
 import { convertClaudeToCursor } from "../converters/claude-to-cursor"
 import { convertClaudeToPi } from "../converters/claude-to-pi"
+import { convertClaudeToGemini } from "../converters/claude-to-gemini"
 import { writeOpenCodeBundle } from "./opencode"
 import { writeCodexBundle } from "./codex"
 import { writeDroidBundle } from "./droid"
 import { writeCursorBundle } from "./cursor"
 import { writePiBundle } from "./pi"
+import { writeGeminiBundle } from "./gemini"
 
 export type TargetHandler<TBundle = unknown> = {
   name: string
@@ -53,4 +56,10 @@ export const targets: Record<string, TargetHandler> = {
     convert: convertClaudeToPi as TargetHandler<PiBundle>["convert"],
     write: writePiBundle as TargetHandler<PiBundle>["write"],
   },
+  gemini: {
+    name: "gemini",
+    implemented: true,
+    convert: convertClaudeToGemini as TargetHandler<GeminiBundle>["convert"],
+    write: writeGeminiBundle as TargetHandler<GeminiBundle>["write"],
+  },
 }

src/types/gemini.ts

@@ -0,0 +1,29 @@
+export type GeminiSkill = {
+  name: string
+  content: string // Full SKILL.md with YAML frontmatter
+}
+
+export type GeminiSkillDir = {
+  name: string
+  sourceDir: string
+}
+
+export type GeminiCommand = {
+  name: string // e.g. "plan" or "workflows/plan"
+  content: string // Full TOML content
+}
+
+export type GeminiMcpServer = {
+  command?: string
+  args?: string[]
+  env?: Record<string, string>
+  url?: string
+  headers?: Record<string, string>
+}
+
+export type GeminiBundle = {
+  generatedSkills: GeminiSkill[] // From agents
+  skillDirs: GeminiSkillDir[] // From skills (pass-through)
+  commands: GeminiCommand[]
+  mcpServers?: Record<string, GeminiMcpServer>
+}

tests/gemini-converter.test.ts

@@ -0,0 +1,373 @@
+import { describe, expect, test } from "bun:test"
+import { convertClaudeToGemini, toToml, transformContentForGemini } from "../src/converters/claude-to-gemini"
+import { parseFrontmatter } from "../src/utils/frontmatter"
+import type { ClaudePlugin } from "../src/types/claude"
+
+const fixturePlugin: ClaudePlugin = {
+  root: "/tmp/plugin",
+  manifest: { name: "fixture", version: "1.0.0" },
+  agents: [
+    {
+      name: "Security Reviewer",
+      description: "Security-focused agent",
+      capabilities: ["Threat modeling", "OWASP"],
+      model: "claude-sonnet-4-20250514",
+      body: "Focus on vulnerabilities.",
+      sourcePath: "/tmp/plugin/agents/security-reviewer.md",
+    },
+  ],
+  commands: [
+    {
+      name: "workflows:plan",
+      description: "Planning command",
+      argumentHint: "[FOCUS]",
+      model: "inherit",
+      allowedTools: ["Read"],
+      body: "Plan the work.",
+      sourcePath: "/tmp/plugin/commands/workflows/plan.md",
+    },
+  ],
+  skills: [
+    {
+      name: "existing-skill",
+      description: "Existing skill",
+      sourceDir: "/tmp/plugin/skills/existing-skill",
+      skillPath: "/tmp/plugin/skills/existing-skill/SKILL.md",
+    },
+  ],
+  hooks: undefined,
+  mcpServers: {
+    local: { command: "echo", args: ["hello"] },
+  },
+}
+
+describe("convertClaudeToGemini", () => {
+  test("converts agents to skills with SKILL.md frontmatter", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const skill = bundle.generatedSkills.find((s) => s.name === "security-reviewer")
+    expect(skill).toBeDefined()
+    const parsed = parseFrontmatter(skill!.content)
+    expect(parsed.data.name).toBe("security-reviewer")
+    expect(parsed.data.description).toBe("Security-focused agent")
+    expect(parsed.body).toContain("Focus on vulnerabilities.")
+  })
+
+  test("agent with capabilities prepended to body", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const skill = bundle.generatedSkills.find((s) => s.name === "security-reviewer")
+    expect(skill).toBeDefined()
+    const parsed = parseFrontmatter(skill!.content)
+    expect(parsed.body).toContain("## Capabilities")
+    expect(parsed.body).toContain("- Threat modeling")
+    expect(parsed.body).toContain("- OWASP")
+  })
+
+  test("agent with empty description gets default description", () => {
+    const plugin: ClaudePlugin = {
+      ...fixturePlugin,
+      agents: [
+        {
+          name: "my-agent",
+          body: "Do things.",
+          sourcePath: "/tmp/plugin/agents/my-agent.md",
+        },
+      ],
+      commands: [],
+      skills: [],
+    }
+
+    const bundle = convertClaudeToGemini(plugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const parsed = parseFrontmatter(bundle.generatedSkills[0].content)
+    expect(parsed.data.description).toBe("Use this skill for my-agent tasks")
+  })
+
+  test("agent model field silently dropped", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const skill = bundle.generatedSkills.find((s) => s.name === "security-reviewer")
+    const parsed = parseFrontmatter(skill!.content)
+    expect(parsed.data.model).toBeUndefined()
+  })
+
+  test("agent with empty body gets default body text", () => {
+    const plugin: ClaudePlugin = {
+      ...fixturePlugin,
+      agents: [
+        {
+          name: "Empty Agent",
+          description: "An empty agent",
+          body: "",
+          sourcePath: "/tmp/plugin/agents/empty.md",
+        },
+      ],
+      commands: [],
+      skills: [],
+    }
+
+    const bundle = convertClaudeToGemini(plugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const parsed = parseFrontmatter(bundle.generatedSkills[0].content)
+    expect(parsed.body).toContain("Instructions converted from the Empty Agent agent.")
+  })
+
+  test("converts commands to TOML with prompt and description", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    expect(bundle.commands).toHaveLength(1)
+    const command = bundle.commands[0]
+    expect(command.name).toBe("workflows/plan")
+    expect(command.content).toContain('description = "Planning command"')
+    expect(command.content).toContain('prompt = """')
+    expect(command.content).toContain("Plan the work.")
+  })
+
+  test("namespaced command creates correct path", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const command = bundle.commands.find((c) => c.name === "workflows/plan")
+    expect(command).toBeDefined()
+  })
+
+  test("command with argument-hint gets {{args}} placeholder", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const command = bundle.commands[0]
+    expect(command.content).toContain("{{args}}")
+  })
+
+  test("command with disable-model-invocation is still included", () => {
+    const plugin: ClaudePlugin = {
+      ...fixturePlugin,
+      commands: [
+        {
+          name: "disabled-command",
+          description: "Disabled command",
+          disableModelInvocation: true,
+          body: "Disabled body.",
+          sourcePath: "/tmp/plugin/commands/disabled.md",
+        },
+      ],
+      agents: [],
+      skills: [],
+    }
+
+    const bundle = convertClaudeToGemini(plugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    // Gemini TOML commands are prompts, not code — always include
+    expect(bundle.commands).toHaveLength(1)
+    expect(bundle.commands[0].name).toBe("disabled-command")
+  })
+
+  test("command allowedTools silently dropped", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    const command = bundle.commands[0]
+    expect(command.content).not.toContain("allowedTools")
+    expect(command.content).not.toContain("Read")
+  })
+
+  test("skills pass through as directory references", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    expect(bundle.skillDirs).toHaveLength(1)
+    expect(bundle.skillDirs[0].name).toBe("existing-skill")
+    expect(bundle.skillDirs[0].sourceDir).toBe("/tmp/plugin/skills/existing-skill")
+  })
+
+  test("MCP servers convert to settings.json-compatible config", () => {
+    const bundle = convertClaudeToGemini(fixturePlugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    expect(bundle.mcpServers?.local?.command).toBe("echo")
+    expect(bundle.mcpServers?.local?.args).toEqual(["hello"])
+  })
+
+  test("plugin with zero agents produces empty generatedSkills", () => {
+    const plugin: ClaudePlugin = {
+      ...fixturePlugin,
+      agents: [],
+      commands: [],
+      skills: [],
+    }
+
+    const bundle = convertClaudeToGemini(plugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    expect(bundle.generatedSkills).toHaveLength(0)
+  })
+
+  test("plugin with only skills works correctly", () => {
+    const plugin: ClaudePlugin = {
+      ...fixturePlugin,
+      agents: [],
+      commands: [],
+    }
+
+    const bundle = convertClaudeToGemini(plugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    expect(bundle.generatedSkills).toHaveLength(0)
+    expect(bundle.skillDirs).toHaveLength(1)
+    expect(bundle.commands).toHaveLength(0)
+  })
+
+  test("agent name colliding with skill name gets deduplicated", () => {
+    const plugin: ClaudePlugin = {
+      ...fixturePlugin,
+      skills: [{ name: "security-reviewer", description: "Existing skill", sourceDir: "/tmp/skill", skillPath: "/tmp/skill/SKILL.md" }],
+      agents: [{ name: "Security Reviewer", description: "Agent version", body: "Body.", sourcePath: "/tmp/agents/sr.md" }],
+      commands: [],
+    }
+
+    const bundle = convertClaudeToGemini(plugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    // Agent should be deduplicated since skill already has "security-reviewer"
+    expect(bundle.generatedSkills[0].name).toBe("security-reviewer-2")
+    expect(bundle.skillDirs[0].name).toBe("security-reviewer")
+  })
+
+  test("hooks present emits console.warn", () => {
+    const warnings: string[] = []
+    const originalWarn = console.warn
+    console.warn = (msg: string) => warnings.push(msg)
+
+    const plugin: ClaudePlugin = {
+      ...fixturePlugin,
+      hooks: { hooks: { PreToolUse: [{ matcher: "*", body: "hook body" }] } },
+      agents: [],
+      commands: [],
+      skills: [],
+    }
+
+    convertClaudeToGemini(plugin, {
+      agentMode: "subagent",
+      inferTemperature: false,
+      permissions: "none",
+    })
+
+    console.warn = originalWarn
+    expect(warnings.some((w) => w.includes("Gemini"))).toBe(true)
+  })
+})
+
+describe("transformContentForGemini", () => {
+  test("transforms .claude/ paths to .gemini/", () => {
+    const result = transformContentForGemini("Read .claude/settings.json for config.")
+    expect(result).toContain(".gemini/settings.json")
+    expect(result).not.toContain(".claude/")
+  })
+
+  test("transforms ~/.claude/ paths to ~/.gemini/", () => {
+    const result = transformContentForGemini("Check ~/.claude/config for settings.")
+    expect(result).toContain("~/.gemini/config")
+    expect(result).not.toContain("~/.claude/")
+  })
+
+  test("transforms Task agent(args) to natural language skill reference", () => {
+    const input = `Run these:
+
+- Task repo-research-analyst(feature_description)
+- Task learnings-researcher(feature_description)
+
+Task best-practices-researcher(topic)`
+
+    const result = transformContentForGemini(input)
+    expect(result).toContain("Use the repo-research-analyst skill to: feature_description")
+    expect(result).toContain("Use the learnings-researcher skill to: feature_description")
+    expect(result).toContain("Use the best-practices-researcher skill to: topic")
+    expect(result).not.toContain("Task repo-research-analyst")
+  })
+
+  test("transforms @agent references to skill references", () => {
+    const result = transformContentForGemini("Ask @security-sentinel for a review.")
+    expect(result).toContain("the security-sentinel skill")
+    expect(result).not.toContain("@security-sentinel")
+  })
+})
+
+describe("toToml", () => {
+  test("produces valid TOML with description and prompt", () => {
+    const result = toToml("A description", "The prompt content")
+    expect(result).toContain('description = "A description"')
+    expect(result).toContain('prompt = """')
+    expect(result).toContain("The prompt content")
+    expect(result).toContain('"""')
+  })
+
+  test("escapes quotes in description", () => {
+    const result = toToml('Say "hello"', "Prompt")
+    expect(result).toContain('description = "Say \\"hello\\""')
+  })
+
+  test("escapes triple quotes in prompt", () => {
+    const result = toToml("A command", 'Content with """ inside it')
+    // Should not contain an unescaped """ that would close the TOML multi-line string prematurely
+    // The prompt section should have the escaped version
+    expect(result).toContain('description = "A command"')
+    expect(result).toContain('prompt = """')
+    // The inner """ should be escaped
+    expect(result).not.toMatch(/""".*""".*"""/s) // Should not have 3 separate triple-quote sequences (open, content, close would make 3)
+    // Verify it contains the escaped form
+    expect(result).toContain('\\"\\"\\"')
+  })
+})

tests/gemini-writer.test.ts

@@ -0,0 +1,181 @@
+import { describe, expect, test } from "bun:test"
+import { promises as fs } from "fs"
+import path from "path"
+import os from "os"
+import { writeGeminiBundle } from "../src/targets/gemini"
+import type { GeminiBundle } from "../src/types/gemini"
+
+async function exists(filePath: string): Promise<boolean> {
+  try {
+    await fs.access(filePath)
+    return true
+  } catch {
+    return false
+  }
+}
+
+describe("writeGeminiBundle", () => {
+  test("writes skills, commands, and settings.json", async () => {
+    const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "gemini-test-"))
+    const bundle: GeminiBundle = {
+      generatedSkills: [
+        {
+          name: "security-reviewer",
+          content: "---\nname: security-reviewer\ndescription: Security\n---\n\nReview code.",
+        },
+      ],
+      skillDirs: [
+        {
+          name: "skill-one",
+          sourceDir: path.join(import.meta.dir, "fixtures", "sample-plugin", "skills", "skill-one"),
+        },
+      ],
+      commands: [
+        {
+          name: "plan",
+          content: 'description = "Plan"\nprompt = """\nPlan the work.\n"""',
+        },
+      ],
+      mcpServers: {
+        playwright: { command: "npx", args: ["-y", "@anthropic/mcp-playwright"] },
+      },
+    }
+
+    await writeGeminiBundle(tempRoot, bundle)
+
+    expect(await exists(path.join(tempRoot, ".gemini", "skills", "security-reviewer", "SKILL.md"))).toBe(true)
+    expect(await exists(path.join(tempRoot, ".gemini", "skills", "skill-one", "SKILL.md"))).toBe(true)
+    expect(await exists(path.join(tempRoot, ".gemini", "commands", "plan.toml"))).toBe(true)
+    expect(await exists(path.join(tempRoot, ".gemini", "settings.json"))).toBe(true)
+
+    const skillContent = await fs.readFile(
+      path.join(tempRoot, ".gemini", "skills", "security-reviewer", "SKILL.md"),
+      "utf8",
+    )
+    expect(skillContent).toContain("Review code.")
+
+    const commandContent = await fs.readFile(
+      path.join(tempRoot, ".gemini", "commands", "plan.toml"),
+      "utf8",
+    )
+    expect(commandContent).toContain("Plan the work.")
+
+    const settingsContent = JSON.parse(
+      await fs.readFile(path.join(tempRoot, ".gemini", "settings.json"), "utf8"),
+    )
+    expect(settingsContent.mcpServers.playwright.command).toBe("npx")
+  })
+
+  test("namespaced commands create subdirectories", async () => {
+    const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "gemini-ns-"))
+    const bundle: GeminiBundle = {
+      generatedSkills: [],
+      skillDirs: [],
+      commands: [
+        {
+          name: "workflows/plan",
+          content: 'description = "Plan"\nprompt = """\nPlan.\n"""',
+        },
+      ],
+    }
+
+    await writeGeminiBundle(tempRoot, bundle)
+
+    expect(await exists(path.join(tempRoot, ".gemini", "commands", "workflows", "plan.toml"))).toBe(true)
+  })
+
+  test("does not double-nest when output root is .gemini", async () => {
+    const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "gemini-home-"))
+    const geminiRoot = path.join(tempRoot, ".gemini")
+    const bundle: GeminiBundle = {
+      generatedSkills: [
+        { name: "reviewer", content: "Reviewer skill content" },
+      ],
+      skillDirs: [],
+      commands: [
+        { name: "plan", content: "Plan content" },
+      ],
+    }
+
+    await writeGeminiBundle(geminiRoot, bundle)
+
+    expect(await exists(path.join(geminiRoot, "skills", "reviewer", "SKILL.md"))).toBe(true)
+    expect(await exists(path.join(geminiRoot, "commands", "plan.toml"))).toBe(true)
+    // Should NOT double-nest under .gemini/.gemini
+    expect(await exists(path.join(geminiRoot, ".gemini"))).toBe(false)
+  })
+
+  test("handles empty bundles gracefully", async () => {
+    const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "gemini-empty-"))
+    const bundle: GeminiBundle = {
+      generatedSkills: [],
+      skillDirs: [],
+      commands: [],
+    }
+
+    await writeGeminiBundle(tempRoot, bundle)
+    expect(await exists(tempRoot)).toBe(true)
+  })
+
+  test("backs up existing settings.json before overwrite", async () => {
+    const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "gemini-backup-"))
+    const geminiRoot = path.join(tempRoot, ".gemini")
+    await fs.mkdir(geminiRoot, { recursive: true })
+
+    // Write existing settings.json
+    const settingsPath = path.join(geminiRoot, "settings.json")
+    await fs.writeFile(settingsPath, JSON.stringify({ mcpServers: { old: { command: "old-cmd" } } }))
+
+    const bundle: GeminiBundle = {
+      generatedSkills: [],
+      skillDirs: [],
+      commands: [],
+      mcpServers: {
+        newServer: { command: "new-cmd" },
+      },
+    }
+
+    await writeGeminiBundle(geminiRoot, bundle)
+
+    // New settings.json should have the new content
+    const newContent = JSON.parse(await fs.readFile(settingsPath, "utf8"))
+    expect(newContent.mcpServers.newServer.command).toBe("new-cmd")
+
+    // A backup file should exist
+    const files = await fs.readdir(geminiRoot)
+    const backupFiles = files.filter((f) => f.startsWith("settings.json.bak."))
+    expect(backupFiles.length).toBeGreaterThanOrEqual(1)
+  })
+
+  test("merges mcpServers into existing settings.json without clobbering other keys", async () => {
+    const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "gemini-merge-"))
+    const geminiRoot = path.join(tempRoot, ".gemini")
+    await fs.mkdir(geminiRoot, { recursive: true })
+
+    // Write existing settings.json with other keys
+    const settingsPath = path.join(geminiRoot, "settings.json")
+    await fs.writeFile(settingsPath, JSON.stringify({
+      model: "gemini-2.5-pro",
+      mcpServers: { old: { command: "old-cmd" } },
+    }))
+
+    const bundle: GeminiBundle = {
+      generatedSkills: [],
+      skillDirs: [],
+      commands: [],
+      mcpServers: {
+        newServer: { command: "new-cmd" },
+      },
+    }
+
+    await writeGeminiBundle(geminiRoot, bundle)
+
+    const content = JSON.parse(await fs.readFile(settingsPath, "utf8"))
+    // Should preserve existing model key
+    expect(content.model).toBe("gemini-2.5-pro")
+    // Should preserve existing MCP server
+    expect(content.mcpServers.old.command).toBe("old-cmd")
+    // Should add new MCP server
+    expect(content.mcpServers.newServer.command).toBe("new-cmd")
+  })
+})