OpenClaw rejects generated plugin manifests that omit configSchema, even for tool plugins with no user configuration. Always emit an empty object schema so converted installs boot cleanly.\n\nAdd converter and writer regression coverage for the manifest shape.\n\nFixes #224
- codex-agents.ts: replace vague "ask the user in chat" with structured
numbered-list instructions for Codex AGENTS.md context
- CLAUDE.md: add AskUserQuestion policy to skill compliance checklist
to prevent recurrence in future skills
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- sync.ts: add gemini + all targets, keep copilot, remove cursor (native), use shared hasPotentialSecrets
- install.ts + convert.ts: import both detectInstalledTools and resolveTargetOutputRoot; update --to all block to use new object API; fix resolvedScope ordering (was referencing target before definition)
- CHANGELOG.md: add v0.12.0 entry (auto-detect + Gemini sync)
- README.md: merge all install targets, collapsible output format table, sync defaults to --target all
- package.json: bump to 0.12.0
- sync --target now defaults to "all" when omitted
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Combine windsurf scope support from this branch with openclaw/qwen targets from main
- Update resolve-output.ts utility to handle openclaw/qwen with openclawHome/qwenHome/pluginName
- Add openclawHome/qwenHome args to install.ts and convert.ts
- Register openclaw and qwen in targets/index.ts alongside windsurf
- Add openclaw/qwen coverage to resolve-output.test.ts (4 new tests → 288 total)
- Update README to document all 10 targets including windsurf and openclaw
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Both openclaw (#217) and qwen (#220) modified install.ts and targets/index.ts.
Combined both targets: openclawHome + qwenHome in resolveTargetOutputRoot,
both registered in the targets registry.
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix P1: Remove dead TOOL_MAP constant (defined but never referenced)
- Fix P1: Replace curl fallback for remote MCP servers with warn-and-skip,
matching the kiro pattern — curl is not an MCP server
- Fix P1: Remove incorrect literal cwd field ("${extensionPath}${/}") from
stdio MCP server config; the value was never interpolated
- Fix P1: Fix plugin.name → plugin.manifest.name in generateContextFile
(plugin.name does not exist on ClaudePlugin; produced "# undefined")
- Fix P1: Wire qwenHome through resolveTargetOutputRoot; previously the
--qwen-home CLI flag was parsed but silently discarded
- Fix P1: Remove hardcoded "compound-engineering" from qwen output path;
now uses plugin.manifest.name via new qwenHome + pluginName params
- Fix P1: Collapse dead-code resolveQwenPaths branches (both returned
identical structures; simplify to a single return)
- Fix P3: Remove rewriting of .opencode/ paths to .qwen/ — Claude plugins
do not reference opencode paths, and rewriting them is incorrect
- Fix P3: inferTemperature now returns undefined for unrecognized agents
instead of 0.3 (matching the explicit doc branch), letting the model
use its default temperature
- Fix P2: Add lookbehind guards to rewriteQwenPaths() matching kiro pattern
to avoid rewriting paths inside compound tokens or URLs
- Update --qwen-home default to ~/.qwen/extensions (plugin name appended)
- Add qwen-converter.test.ts with 16 tests covering all scenarios
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix P1: Replace incomplete string escaping in generateEntryPoint with
JSON.stringify() to prevent code injection via command names/descriptions
with backslashes, newlines, or other special characters
- Fix P1: Remove hardcoded 'compound-engineering' output path; resolve
from plugin.manifest.name via new openclawHome + pluginName params
- Fix P2: Add --openclaw-home CLI flag (default: ~/.openclaw/extensions)
consistent with --codex-home and --pi-home patterns
- Fix P2: Emit typed `const skills: Record<string, string> = {}` in
generated TypeScript to prevent downstream type errors
- Fix P3: Add lookbehind guards to rewritePaths() matching kiro pattern
- Fix P3: Extract duplicated disableModelInvocation filter to variable
- Fix P3: Build manifest skills list before constructing manifest object
(no post-construction mutation)
- Export ClaudeToOpenClawOptions type alias for interface clarity
- Add openclaw-converter.test.ts with 13 tests covering all scenarios
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix resolve-pr-parallel SKILL.md name from underscores to hyphens
(must match directory name per Windsurf spec)
- Add scope parameter to TargetHandler.write signature
- Pass resolvedScope through to writer in convert.ts and install.ts
- Windsurf writer uses global_workflows/ for global scope, workflows/
for workspace scope
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add `--to windsurf` target for the converter CLI with full spec compliance
per docs/specs/windsurf.md:
- Claude agents → Windsurf skills (skills/{name}/SKILL.md)
- Claude commands → Windsurf workflows (workflows/{name}.md, flat)
- Pass-through skills copy unchanged
- MCP servers → mcp_config.json (merged with existing, 0o600 permissions)
- Hooks skipped with warning, CLAUDE.md skipped
Global scope support via generic --scope flag (Windsurf as first adopter):
- --to windsurf defaults to global (~/.codeium/windsurf/)
- --scope workspace for project-level .windsurf/ output
- --output overrides scope-derived paths
Shared utilities extracted (resolveTargetOutputRoot, hasPotentialSecrets)
to eliminate duplication across CLI commands.
68 new tests (converter, writer, scope resolution).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Stop stripping namespace prefixes when converting commands to Copilot
skills. `workflows:plan` now becomes `workflows-plan` instead of just
`plan`, avoiding clashes with Copilot's own features in the chat UI.
Also updates slash command references in body text to match:
`/workflows:plan` → `/workflows-plan`.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add copilot case to resolveTargetOutputRoot so `install --to copilot`
writes to .github/ in the current directory instead of falling through
to the opencode default (~/.config/opencode).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The copilot entry in the targets record was missing its closing `},`
after merging with the gemini target branch, causing a parse error.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Extract named GeminiMcpServer type (eliminates NonNullable indexing)
- Deep-merge mcpServers in settings.json (preserves existing entries)
- Warn when existing settings.json cannot be parsed
- Add test for uniqueName dedup (agent/skill name collision)
- Add test for TOML triple-quote escaping
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add `--to gemini` support for both `convert` and `install` commands,
converting Claude Code plugins into Gemini CLI-compatible format.
- Agents convert to `.gemini/skills/*/SKILL.md` with description frontmatter
- Commands convert to `.gemini/commands/*.toml` with TOML prompt format
- Namespaced commands create directory structure (workflows:plan -> workflows/plan.toml)
- Skills pass through unchanged (identical SKILL.md standard)
- MCP servers written to `.gemini/settings.json` with merge support
- Content transforms: .claude/ paths, Task calls, @agent references
- Hooks emit warning (different format in Gemini)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add Copilot as the 6th converter target, transforming Claude Code plugins
into Copilot's native format: custom agents (.agent.md), agent skills
(SKILL.md), and MCP server configuration JSON.
Component mapping:
- Agents → .github/agents/{name}.agent.md (with Copilot frontmatter)
- Commands → .github/skills/{name}/SKILL.md
- Skills → .github/skills/{name}/ (copied as-is)
- MCP servers → .github/copilot-mcp-config.json
- Hooks → skipped with warning
Also adds `compound sync copilot` support and fixes YAML quoting for
the `*` character in frontmatter serialization.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add sync --target droid (skills to ~/.factory/skills/)
- Add sync --target cursor (skills + MCP to .cursor/)
- Extract expandHome/resolveTargetHome to src/utils/resolve-home.ts
- Remove duplicated path helpers from convert.ts and install.ts
- Bump version to 0.6.0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
normalizeModel() turned bare aliases like 'haiku' into 'anthropic/haiku',
which is not a valid OpenCode model ID. This caused
ProviderModelNotFoundError when agents using model: haiku (e.g.
learnings-researcher, lint) were invoked during workflows like /plan.
Add CLAUDE_FAMILY_ALIASES map to resolve haiku, sonnet, and opus to their
full model IDs (e.g. anthropic/claude-haiku-4-5). A console.warn alerts
during conversion so the map can be updated when new versions release.
* feat(cursor): add Cursor CLI as target provider
Add converter, writer, types, and tests for converting Claude Code
plugins to Cursor-compatible format (.mdc rules, commands, skills,
mcp.json). Agents become Agent Requested rules (alwaysApply: false),
commands are plain markdown, skills copy directly, MCP is 1:1 JSON.
* docs: add Cursor spec and update README with cursor target
* chore: bump CLI version to 0.5.0 for cursor target
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: note Cursor IDE + CLI compatibility in README
* fix: install by name always fetches from GitHub
Previously, `install compound-engineering` would resolve to any local
directory named `compound-engineering` in the current working directory
before trying GitHub. This broke installs when users had a same-named
directory that wasn't a valid plugin.
Now bare names always go to GitHub. Only explicit paths (starting with
./ or / or ~) are treated as local paths.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(cursor): add Cursor CLI as target provider
Add converter, writer, types, and tests for converting Claude Code
plugins to Cursor-compatible format (.mdc rules, commands, skills,
mcp.json). Agents become Agent Requested rules (alwaysApply: false),
commands are plain markdown, skills copy directly, MCP is 1:1 JSON.
* docs: add Cursor spec and update README with cursor target
* chore: bump CLI version to 0.5.0 for cursor target
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: note Cursor IDE + CLI compatibility in README
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(commands): add /compound-engineering-setup for configurable agents
Adds a new setup command that allows users to configure which review
agents to use instead of hardcoding them in workflows. This enables:
- Multi-step onboarding with AskUserQuestion for easy setup
- Auto-detection of project type (Rails, Python, TypeScript, etc.)
- Three setup modes: Quick (smart defaults), Advanced, and Minimal
- Configuration stored in .claude/compound-engineering.json
- Support for both global (~/.claude/) and project-specific config
Updated workflows to read from config:
- /workflows:review - reads reviewAgents from config
- /plan_review - reads planReviewAgents from config
- /workflows:work - references config for reviewer agents
- /workflows:compound - references config for specialized agents
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: auto-trigger setup when no config exists
Workflows now detect missing config and offer inline quick setup:
- "Quick Setup" - auto-detect project type, create config, continue
- "Full Setup" - run /compound-engineering-setup for customization
- "Skip" - use defaults just this once
This ensures users get onboarded automatically when running any
workflow for the first time, without needing to know about the
setup command beforehand.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(review): wire all conditionalAgents categories
Extended /workflows:review to invoke conditional agents for:
- migrations (existing)
- frontend (new): JS/TS/Stimulus changes
- architecture (new): structural changes, 10+ files
- data (new): model/ActiveRecord changes
Each category reads from conditionalAgents.* config key and
runs appropriate specialized agents when file patterns match.
Resolves: todos/001-ready-p2-conditional-agents-not-invoked.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: mark todo #001 as complete
* feat(setup): add custom agent discovery and modify flow
- Auto-detect custom agents in .claude/agents/ and ~/.claude/agents/
- Add modify existing config flow (add/remove agents, view config)
- Include guide for creating custom review agents
- Add customAgents mapping in config to track agent file paths
- Update changelog with new config schema including customAgents
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: remove completed todos directory
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* [2.29.1] Improve /workflows:brainstorm question flow
- Add "Ask more questions" option at handoff phase
- Clarify that Claude should ask the user questions (not wait for user)
- Require resolving ALL open questions before offering to proceed
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Simplify plugin settings: replace 486-line wizard with .local.md pattern
- Rewrite setup.md (486 → 95 lines): detect project type, create
.claude/compound-engineering.local.md with smart defaults
- Make review.md and work.md config-aware: read agents from .local.md
frontmatter, fall back to auto-detected defaults
- Wire schema-drift-detector into review.md migrations conditional block
- Delete technical_review.md (duplicated /plan_review)
- Add disable-model-invocation to setup.md
- Bump to v2.32.0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Rewrite .claude/ paths for OpenCode/Codex targets, add npm publish workflow
- Converters now rewrite .claude/ → .opencode/ (OpenCode) and .codex/ (Codex)
in command bodies and agent bodies so .local.md settings work cross-platform
- Apply transformContentForCodex to agent bodies (was only commands before)
- Add GitHub Action to auto-publish to npm on version bump merge to main
- Bump to v0.4.0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(workflows-work): require post-deploy monitoring section
Add a mandatory Post-Deploy Monitoring & Validation section to the /workflows:work PR template, include no-impact fallback guidance, and enforce it in the quality checklist.
* Add learnings-researcher to review workflow, fix docs site counts
- Add learnings-researcher as parallel agent #14 in /workflows:review
so past solutions from docs/solutions/ are surfaced during code review
- Make /release-docs command invocable (remove disable-model-invocation)
- Fix stale counts across docs site (agents 28→29, commands 19→24,
skills 15→18, MCP servers 2→1)
- Bump version to 2.32.1
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Move /release-docs to local .claude/commands/, bump to 2.32.2
Repo maintenance command doesn't need to be distributed to plugin users.
Update command count 24 → 23 across plugin.json, marketplace.json, and docs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Move settings to project root: compound-engineering.local.md
Tool-agnostic location — works for Claude, Codex, OpenCode without
path rewriting. No global fallback, just project root.
Update commands (setup, review, work) and converter tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Make /compound-engineering-setup interactive with auto-detect fast path
Two paths: "Auto-configure" (one click, smart defaults) or "Customize"
(pick stack, focus areas, review depth). Uses AskUserQuestion throughout.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Replace /compound-engineering-setup command with setup skill
Setup is now a skill invoked on-demand when compound-engineering.local.md
doesn't exist. Review and work commands just say "invoke the setup skill"
instead of inlining the full setup flow.
- Remove commands/setup.md (command)
- Add skills/setup/SKILL.md (skill with interactive AskUserQuestion flow)
- Simplify review.md and work.md to reference the skill
- Counts: 29 agents, 22 commands, 19 skills
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Prepare v2.33.0 release: setup skill, configurable review agents
- Bump version to 2.33.0
- Consolidate CHANGELOG entries for this branch
- Fix README: update counts (29/22/19), add setup + resolve-pr-parallel skills
- Remove stale /compound-engineering-setup command reference
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Adds a new 'droid' target to the converter that outputs Claude Code plugins
in Factory Droid's format:
- Commands flattened to ~/.factory/commands/ (strips namespace prefixes)
- Agents converted to droids in ~/.factory/droids/ with proper frontmatter
- Skills copied to ~/.factory/skills/
- Content transforms: Task calls, slash commands, and @agent references
adapted to Droid conventions
This resolves the manual workaround described in issue #31 by automating
the conversion from Claude Code plugin format to Factory Droid's expected
directory structure.
Includes 13 tests covering converter logic and file writer behavior.
Co-authored-by: adamprime <adamprime@hey.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* Update create-agent-skills to match 2026 official docs, add /triage-prs command
- Rewrite SKILL.md to document that commands and skills are now merged
- Add new frontmatter fields: disable-model-invocation, user-invocable, context, agent
- Add invocation control table and dynamic context injection docs
- Fix skill-structure.md: was incorrectly recommending XML tags over markdown headings
- Update official-spec.md with complete 2026 specification
- Add local /triage-prs command for PR triage workflow
- Add PR triage plan document
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* [2.31.0] Reduce context token usage by 79%, include recent community contributions
The plugin was consuming 316% of Claude Code's description character budget
(~50,500 chars vs 16,000 limit), causing components to be silently excluded.
Now at 65% (~10,400 chars) with all components visible.
Changes:
- Trim all 29 agent descriptions (move examples to body)
- Add disable-model-invocation to 18 manual commands
- Add disable-model-invocation to 6 manual skills
- Include recent community contributions in changelog
- Fix component counts (29 agents, 24 commands, 18 skills)
Contributors: @trevin, @terryli, @robertomello, @zacwilliams,
@aarnikoskela, @samxie, @davidalley
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix: keep disable-model-invocation off commands called by /lfg, rename xcode-test
- Remove disable-model-invocation from test-browser, feature-video,
resolve_todo_parallel — these are called programmatically by /lfg and /slfg
- Rename xcode-test to test-xcode to match test-browser naming convention
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix: keep git-worktree skill auto-invocable (used by /workflows:work)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(converter): support disable-model-invocation frontmatter
Parse disable-model-invocation from command and skill frontmatter.
Commands/skills with this flag are excluded from OpenCode command maps
and Codex prompt/skill generation, matching Claude Code behavior where
these components are user-only invocable.
Bump converter version to 0.3.0.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Claude Code allows hook entries without a `matcher` field (e.g.,
SessionStart and SubagentStop hooks don't need one). The OpenCode
converter assumed `matcher.matcher` was always present, causing
"undefined is not an object (evaluating 'matcher.matcher.split')"
when converting plugins with matcher-less hooks.
Make `matcher` optional in the type and guard all accesses.
Before writing config.toml (Codex) or opencode.json (OpenCode), the CLI
attempts to create a timestamped backup of any existing config file.
This prevents accidental data loss when users have customized configs.
Backup is best-effort - if it fails (e.g., unusual permissions), the
install continues without blocking.
Backup files are named: config.toml.bak.2026-01-23T21-16-40-065Z
Adds comprehensive content transformation for Codex compatibility:
1. Task agent calls: `Task agent-name(args)` → `Use the $agent-name skill to: args`
2. Slash commands: `/command-name` → `/prompts:command-name`
3. Agent references: `@agent-name` → `$agent-name skill`
This bridges the syntax gap between Claude Code and Codex:
- Claude Code uses Task tool with subagent_types
- Codex uses skills and /prompts: namespace
Transformations are applied to both skill and prompt files during conversion.
Tested with Codex CLI 0.89.0 - all transformations working correctly.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
The OpenCode installer was writing to ~/.opencode but OpenCode expects
global configuration at ~/.config/opencode per XDG Base Directory spec.
Fixes:
- src/commands/install.ts: Change default output from ~/.opencode to
~/.config/opencode
- src/targets/opencode.ts: Recognize "opencode" basename (not just
".opencode") for direct writes without nesting
Closes#114🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
