New issue-intelligence-analyst agent that fetches GitHub issues via
gh CLI, clusters by root-cause themes, and returns structured analysis
with trend direction, confidence scores, and source mix. Designed for
both ce:ideate integration and standalone use.
Agent design:
- Priority-aware fetching with label scanning for focus targeting
- Truncated bodies (500 chars) in initial fetch to avoid N+1 calls
- Single gh call per fetch, no pipes or scripts (avoids permission spam)
- Built-in --jq for all field extraction and filtering
- Mandatory structured output with self-check checklist
- Accurate counts from actual data, not assumptions
- Closed issues as recurrence signal only, not standalone evidence
ce:ideate gains:
- Issue-tracker intent detection in Phase 0.2
- Conditional agent dispatch in Phase 1 (parallel with existing scans)
- Dynamic frame derivation from issue clusters in Phase 2
- Hybrid strategy: cluster-derived frames + default padding when < 4
- Resume awareness distinguishing issue vs non-issue ideation
- Numbered table format for rejection summary in ideation artifacts
Reduce per-agent idea target from 10 to 7-8 based on real usage data
showing ideas 8-11 were speculative tail that rarely survived filtering.
This keeps the unique candidate pool manageable (~20-30 after dedup)
while preserving frame diversity across 4-6 agents. Also add scannable
overview line before detail blocks in Phase 4, and clarify foreground
dispatch and native tool usage in Phase 1.
- Clarify sub-agent volume: each agent targets ~10 ideas (40-60 raw, ~30-50 after dedupe)
- Reframe ideation lenses as starting biases, not constraints, to encourage cross-cutting ideas
- Add orchestrator synthesis step between merge/dedupe and critique
- Improve skill description with specific trigger phrases for better auto-discovery
- Update argument-hint to be user-facing ("feature, focus area, or constraint")
- Position ideate as optional entry point in workflow diagram, not part of core loop
- Update plugin metadata and README with new skill counts and descriptions
* docs: capture codex skill prompt model
* fix: align codex workflow conversion
* chore: remove deprecated workflows:* skill aliases
The workflows:brainstorm, workflows:plan, workflows:work, workflows:review,
and workflows:compound aliases have been deprecated long enough. Remove them
and update skill counts (46 → 41) across plugin.json, marketplace.json,
README, and CLAUDE.md.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Trevin Chow <trevin@trevinchow.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: make PR/commit attribution specific to model, harness, and plugin version
Replace generic "Generated with Claude Code" footer with dynamic attribution
that includes the actual model name, harness tool, and plugin version. LLMs
fill in their own values at commit/PR time. Subagents are explicitly
instructed to do the same.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* style: format attribution substitution guide as table
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* style: rename badge to "Compound Engineering v[VERSION]"
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add context window and thinking level to attribution
Separate MODEL into MODEL, CONTEXT, and THINKING placeholders
so each detail is its own table row and easier to read.
Co-Authored-By: Claude Opus 4.6 (1M context, extended thinking) <noreply@anthropic.com>
* style: badge on its own line, model details on next line in PR template
Co-Authored-By: Claude Opus 4.6 (1M context, extended thinking) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The Phase 0 vibes-based heuristic warned users and forced a mode choice
even with 80%+ context remaining. Full mode now runs by default;
compact-safe mode stays available on explicit request.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The model was offering "commit to current branch" on main instead
of "create a branch and PR." Added explicit branch detection step
and "Do NOT commit directly to main" instruction.
Let the agent generate a reasonable branch name based on context
and repo conventions instead of prescribing a date-based format
that would collide on multiple runs per day.
Handles committing changes at the end of a refresh run so doc
maintenance doesn't sit uncommitted. Detects git context and adapts:
autonomous mode uses sensible defaults (branch + PR on main, separate
commit on feature branches), interactive mode presents options. Always
selectively stages only compound-refresh files to avoid mixing with
in-progress feature work.
The file-tools-over-bash instruction was in the orchestrator's
context but not passed to spawned subagents. Changed to an explicit
quoted instruction block that must be included in each subagent's
task prompt so it's visible to the subagent, not just the orchestrator.
Auto-archive now requires both the implementation AND the problem
domain to be gone. If referenced files are deleted but the application
still deals with the same problem (auth, payments, migrations), the
learning should be Replace'd not Archive'd — the knowledge gap needs
to be filled. Uses agent reasoning about concepts, not mechanical
keyword searches.
The model was generating findings internally then outputting a
one-line summary. Added explicit instructions that the full report
must be printed as text output — every file, every classification,
every action. In autonomous mode, the report is the sole deliverable
and must be self-contained and complete.
- Restructure Phase 3 with explicit autonomous skip section that says
"do not ask, do not present, do not wait" before any interactive
instructions
- Add autonomous caveats to Core Rules 4, 7, 8 which previously had
unconditional "ask the user" language
- Clarify that missing referenced files is unambiguous Archive evidence,
not a doubt case requiring user input
Instead of requiring write permissions, autonomous mode attempts
writes and gracefully falls back to recommendations when denied.
Report splits into Applied (succeeded) and Recommended (could not
write) sections. Read-only invocations produce a maintenance plan.
Support mode:autonomous argument for unattended/scheduled runs.
In autonomous mode: skip all user questions, apply safe actions
directly, mark ambiguous cases as stale with conservative confidence,
and generate a detailed report for after-the-fact human review.
- Broad scope triage: inventory + impact clustering + spot-check drift
for 9+ docs, recommends highest-impact area instead of blind ask
- Drift classification: sharp boundary between Update (fix references
in-skill) and Replace (subagent writes successor learning)
- Replacement subagents: sequential subagents write new learnings using
ce:compound's document format with investigation evidence already
gathered, avoiding redundant research
- Stale fallback: when evidence is insufficient for a confident
replacement, mark as stale and recommend ce:compound later
- Use platform-agnostic interactive question tool phrasing with examples
for Claude Code and Codex instead of hardcoding AskUserQuestion
- Fix contradiction between Phase 2 auto-archive criteria and Phase 3
always-ask-before-archive rule so unambiguous archives proceed without
unnecessary user prompts
Adds a new skill that reviews existing docs/solutions/ learnings against the
current codebase and decides whether to keep, update, replace, or archive them.
Also enhances ce:compound with Phase 2.5 selective refresh checks.
Co-Authored-By: Claude <noreply@anthropic.com>
Name specific blocking question tools (AskUserQuestion, request_user_input,
ask_user) so agents actually invoke them instead of printing questions as
text output. Updates skill compliance checklist to match.
Add a highest-leverage-move question to the product pressure test,
a challenger option in approach exploration, and a low-cost change
check to the finalization checklist.
Rebased onto main after #251 restructured commands into skills/.
Applied the same namespace fix to the new skill file locations
(ce-brainstorm, ce-plan, ce-review SKILL.md files).
Short agent names like `repo-research-analyst` are replaced with
fully-qualified `compound-engineering:research:repo-research-analyst`
to ensure correct agent resolution across all plugin targets.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Anthropic now maintains a better skill-creator at
github.com/anthropics/skills/tree/main/skills/skill-creator.
Removes the bundled skill-creator and updates component counts
from 47 to 46 skills.
The /technical_review command was removed in v2.32.0 but references
remained in ce:plan and deepen-plan menus. Remove them entirely -
the existing 'Review and refine' option (document-review) already
covers plan review.
Fixes#244
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move all 27 command .md files from commands/ to skills/*/SKILL.md
format. Claude Code 2.1.3+ merged commands and skills - both create
slash commands and work identically. Skills add optional features
like supporting files and automatic context loading.
- commands/ce/*.md -> skills/ce-*/SKILL.md
- commands/workflows/*.md -> skills/workflows-*/SKILL.md
- commands/*.md -> skills/*/SKILL.md
- Update plugin.json and marketplace.json descriptions
- Update CLAUDE.md directory structure docs
- Update deploy-docs and generate_command references
Fixes#116
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The `create-agent-skills` SKILL.md contained literal `!`command`` dynamic
context injection directives as documentation examples. Claude Code's
preprocessor executes these directives as plain text before the skill
content is sent to the model — it does not parse markdown, so fenced code
blocks and inline code spans offer no protection.
When loading this skill, the preprocessor attempted to run `command`,
`gh pr diff`, and `gh pr diff --name-only` as shell commands, producing:
Bash command failed for pattern "!`command`":
(eval):1: redirection with no command
This caused the skill to fail silently or error on every invocation.
Fix: replace the literal directives with a prose description of the
syntax, add a warning about the preprocessor behavior, and link to
`references/official-spec.md` § "Dynamic Context Injection" for the
concrete example (reference files are loaded on-demand by Claude via the
Read tool and are not preprocessed).
Upstream context:
- anthropics/claude-code#27149 (closed, wontfix): preprocessor correctly
executes bare text; workaround is to describe the syntax in prose
- anthropics/claude-code#28024 (closed as duplicate of #13655)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Documents all missing agent-browser CLI commands for debugging workflows.
Adds 9 new command categories: eval, console/errors, network, storage,
device settings, element debugging, recording/tracing, tabs, and
advanced mouse controls.
Closes#170
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Move Interaction Method preamble to after H1 in create-new-skill.md
(was incorrectly placed before the # heading)
- Add same preamble to add-workflow.md which also references AskUserQuestion
in Step 3 without a fallback instruction
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Instructs the LLM to use numbered-list prompts when AskUserQuestion
is unavailable (Codex, Gemini, Copilot, etc.), preventing silent
auto-configuration on non-Claude platforms. Fixes#204.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Merges feat/proof-integration with conflict resolution:
- proof skill for creating/editing/sharing markdown docs via Proof API
- "Share to Proof" added as opt-in menu option in /workflows:brainstorm Phase 4
- "Share to Proof" added as opt-in menu option in /workflows:plan Post-Generation Options
- Bumped version 2.36.0 → 2.37.0 to avoid conflict with OpenClaw/Qwen/Windsurf release
🤖 Generated with [Claude Code](https://claude.com/claude-code)
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 proof skill for collaborative document editing via Proof's web API
and local bridge. Integrate Proof uploads into brainstorm and plan
workflows so outputs get a shareable URL automatically.
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>
Rewrite all reference files, asset templates, and SKILL.md to use
current API patterns (.call(), result.field, T::Enum classes,
Tools::Base). Add two new reference files (toolsets, observability)
covering tools DSL, event system, and Langfuse integration.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
