Codex CLI requires YAML frontmatter (---) in SKILL.md files.
6 skills were missing frontmatter entirely; laravel-verification had
a bare colon in its description causing an invalid YAML parse error.
- Remove prompt_file immediately after shell expansion into -p arg,
avoiding stale temp files during long analysis windows (greptile feedback)
- Update test assertion to check analysis_relpath instead of analysis_file,
matching the cross-platform relative path change from earlier commits
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
The cd "$PROJECT_DIR" failure path returned without removing prompt_file
and analysis_file, leaving stale temp files in .observer-tmp/.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
Address reviewer feedback: under set +e, a failing cd would silently
leave CWD unchanged, causing the relative analysis path to break.
Add || return with a diagnostic log entry.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
Reviewers correctly identified that the relative analysis_relpath
(.observer-tmp/<file>) only resolves when CWD equals PROJECT_DIR.
Without an explicit cd, non-Windows users launching the observer from
a different directory would fail to read the analysis file.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
Address remaining issues from #842 after PR #903 moved temp files to
PROJECT_DIR/.observer-tmp:
Bug A (path resolution): Use relative paths (.observer-tmp/filename)
in the prompt instead of absolute paths from mktemp. On Windows
Git Bash/MSYS2, absolute paths use MSYS-style prefixes (/c/Users/...)
that the spawned Claude subprocess may fail to resolve.
Bug B (asks for permission): Add explicit IMPORTANT instruction block
at the prompt start telling the Haiku agent it is in non-interactive
--print mode and must use the Write tool directly without asking for
confirmation.
Additional improvements:
- Pass prompt via -p flag instead of stdin redirect for Windows compat
- Add .observer-tmp/ to .gitignore to prevent accidental commits
Fixes#842
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
* feat(skills): add santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents evaluate output against a shared rubric. Both must pass before shipping. Includes architecture diagram, implementation patterns (subagent, inline, batch sampling), domain-specific rubric extensions, failure mode mitigations, and integration guidance with existing ECC skills.
* Enhance SKILL.md with detailed Santa Method documentation
Expanded the SKILL.md documentation for the Santa Method, detailing architecture, phases, implementation patterns, failure modes, integration with other skills, metrics, and cost analysis.
* feat: add pending instinct TTL pruning and /prune command
Pending instincts generated by the observer accumulate indefinitely
with no cleanup mechanism. This adds lifecycle management:
- `instinct-cli.py prune` — delete pending instincts older than 30 days
(configurable via --max-age). Supports --dry-run and --quiet flags.
- Enhanced `status` command — shows pending count, warns at 5+,
highlights instincts expiring within 7 days.
- `observer-loop.sh` — runs prune before each analysis cycle.
- `/prune` slash command — user-facing command for manual pruning.
Design rationale: council consensus (4/4) rejected auto-promote in
favor of TTL-based garbage collection. Frequency of observation does
not establish correctness. Unreviewed pending instincts auto-delete
after 30 days; if the pattern is real, the observer will regenerate it.
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
* fix: remove duplicate functions, broaden extension filter, fix prune output
- Remove duplicate _collect_pending_dirs and _parse_created_date defs
- Use ALLOWED_INSTINCT_EXTENSIONS (.md/.yaml/.yml) instead of .md-only
- Track actually-deleted items separately from expired for accurate output
- Update README.md and AGENTS.md command counts: 59 → 60
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
* fix: address Copilot and CodeRabbit review findings
- Use is_dir() instead of exists() for pending path checks
- Change > to >= for --max-age boundary (--max-age 0 now prunes all)
- Use CLV2_PYTHON_CMD env var in observer-loop.sh prune call
- Remove unused source_dupes variable
- Remove extraneous f-string prefix on static string
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
* fix: update AGENTS.md project structure command count 59 → 60
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: address cubic and coderabbit review findings
- Fix status early return skipping pending instinct warnings (cubic #1)
- Exclude already-expired items from expiring-soon filter (cubic #2)
- Warn on unparseable pending instinct age instead of silent skip (cubic #4)
- Log prune failures to observer.log instead of silencing (cubic #5)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: YAML single-quote unescaping, f-string cleanup, add /prune to README
- Fix single-quoted YAML unescaping: use '' doubling (YAML spec) not
backslash escaping which only applies to double-quoted strings (greptile P1)
- Remove extraneous f-string prefix on static string (coderabbit)
- Add /prune to README command catalog and file tree (cubic)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
New debugging skill that traces every button/touchpoint through its full
state change sequence. Catches bugs where functions individually work but
cancel each other out via shared state side effects.
Covers 6 bug patterns:
1. Sequential Undo — call B resets what call A just set
2. Async Race — double-click bypasses state-based loading guards
3. Stale Closure — useCallback captures old value
4. Missing State Transition — handler doesn't do what label says
5. Conditional Dead Path — condition always false, action unreachable
6. useEffect Interference — effect undoes button action
Battle-tested: found 48 bugs in a production React+Zustand app that
systematic debugging (54 bugs found separately) completely missed.
* feat(skills): add Kysely migration patterns to database-migrations
Add Kysely section covering kysely-ctl CLI workflow, migration file
structure (up/down with Kysely<any>), and programmatic Migrator setup
with FileMigrationProvider and allowUnorderedMigrations option.
* fix(skills): address PR review feedback for Kysely migration patterns
- Replace redundant email index with avatar_url index (unique already creates index)
- Add ESM-compatible __dirname using import.meta.url
- Comment out allowUnorderedMigrations with production safety warning
- Add clarifying comment for db variable
* fix(skills): fix migration filename mismatch and clarify ESM-only pattern
- Rename migration file to create_user_profile to match actual content
- Restructure ESM import pattern to be clearly ESM-only with CJS note
Library-agnostic Flutter/Dart code reviewer that adapts to the project's
chosen state management solution (BLoC, Riverpod, Provider, GetX, MobX,
Signals) and architecture pattern (Clean Architecture, MVVM, feature-first).
Co-authored-by: Maciej Starosielec <maciej@code-snap.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace node -e with temp file execution in validator tests to avoid
Windows shebang parsing failures (node -e cannot handle scripts that
originally contained #!/usr/bin/env node shebangs)
- Remove duplicate blank line in skills/rust-patterns/SKILL.md (MD012)
* feat(skills): add architecture-decision-records skill
Adds a skill that captures architectural decisions made during coding
sessions as structured ADR documents (Michael Nygard format).
Features:
- Auto-detects decision moments from conversation signals
- Records context, alternatives considered with pros/cons, and consequences
- Maintains numbered ADR files in docs/adr/ with an index
- Supports ADR lifecycle (proposed → accepted → deprecated/superseded)
- Categorizes decisions worth recording vs trivial ones to skip
- Integrates with planner, code-reviewer, and codebase-onboarding skills
Includes Antigravity support via .agents/skills/ and openai.yaml.
* fix: address review feedback on ADR skill
- Add missing "why did we choose X?" read-ADR trigger to .agents/ copy
- Add canonical-reference link to .agents/ SKILL.md pointing to full version
- Remove integration reference to non-existent codebase-onboarding skill
* fix: add initialization step and sync .agents/ trigger
- Add Step 1 to workflow: initialize docs/adr/ directory, README.md
index, and template.md on first use when directory doesn't exist
- Add "API design" to .agents/ alternatives trigger to match canonical
version
* fix: address ADR workflow gaps and implicit signal safety
- Init step: seed README.md with index table header so Step 8 can
append rows correctly on first ADR
- Add read-path workflow: graceful handling when docs/adr/ is empty
or absent ("No ADRs found, would you like to start?")
- Implicit signals: add "do not auto-create without user confirmation"
guard, tighten triggers to require conclusion/rationale not just
discussion, remove overly broad "testing strategy" trigger
* fix: require user confirmation before creating files
- Canonical SKILL.md: init step now asks user before creating docs/adr/
- .agents/ condensed version: add confirmation gate for implicit signals
and explicit consent step before any file writes
* fix: require user approval before writing ADR file, add refusal path
* fix: remove .agents/ duplicate, keep canonical in skills/
---------
Co-authored-by: vazidmansuri005 <vazidmansuri005@users.noreply.github.com>
* feat(commands): add /context-budget optimizer command
Adds a command that audits context window token consumption across
agents, skills, rules, MCP servers, and CLAUDE.md files.
Detects bloated agent descriptions, redundant components, MCP
over-subscription, and CLAUDE.md bloat. Produces a prioritized
report with specific token savings per optimization.
Directly relevant to #434 (agent descriptions too verbose, ~26k
tokens causing performance warnings).
* fix: address review feedback on context-budget command
- Add $ARGUMENTS to enable --verbose flag passthrough
- Fix MCP token estimate: 45 tools × ~500 tokens = ~22,500 (was ~2,200)
- Fix heavy agents example: all 3 now exceed 200-line threshold
- Fix description threshold: warning at >30 words, fail at >50 words
- Add Step 4 instructions (was empty)
- Fix audit cadence: "quarterly" → "regularly" + "monthly" consistently
- Fix Output Format heading level under Step 4
- Replace "Antigravity" with generic "harness versions"
- Recalculate total overhead to match corrected MCP numbers
* fix: correct MCP tool count and savings percentage in sample output
- Fix MCP tool count: table now shows 87 tools matching the issues
section (was 45 in table vs 87 in issues)
- Fix savings percentage: 5,100 / 66,400 = 7.7% (was 20.6%)
- Recalculate total overhead and effective context to match
* fix: correct sample output arithmetic
- Fix total overhead: 66,400 → 66,100 to match component table sum
(12,400 + 6,200 + 2,800 + 43,500 + 1,200 = 66,100)
- Fix MCP savings: ~1,500 → ~27,500 tokens (55 tools × 500 tokens/tool)
to match the per-tool formula defined in Step 1
- Reorder optimizations by savings (MCP removal is now #1)
- Fix total savings and percentage (31,100 / 66,100 = 47.0%)
* fix: distinguish always-on vs on-demand agent overhead
Agent descriptions are always loaded into Task tool routing context,
but the full agent body is only loaded when invoked. The audit now
measures both: description-only tokens as always-on overhead and
full-file tokens as worst-case overhead. This resolves the
contradiction between Step 1 (counting full files) and Tip 1 (saying
only descriptions are loaded per session).
* fix: simplify agent accounting and resolve inconsistencies
- Revert to single agent overhead metric (full file tokens) — simpler
and matches what the report actually displays
- Add back 200-line threshold for heavy agents in Step 1
- Fix heavy agents action to match issue type (split/trim, not
description-only)
- Remove .agents/skills/ scan path (doesn't exist in ECC repo)
- Consolidate description threshold to single 30-word check
* fix: add model assumption and verbose mode activation
- Step 4: assume 200K context window by default (Claude has no way to
introspect its model at runtime)
- Step 4: add explicit instruction to check $ARGUMENTS for --verbose
flag and include additional output when present
* fix: handle .agents/skills/ duplicates in skill scan
Skills scan now checks .agents/skills/ for Codex harness copies and
skips identical duplicates to avoid double-counting overhead.
* fix: add savings estimate to heavy agents action for consistency
* feat(skills): add context-budget backing skill, slim command to delegator
* fix: use structurally detectable classification criteria instead of session frequency
---------
Co-authored-by: vazidmansuri005 <vazidmansuri005@users.noreply.github.com>
* feat(skills): add codebase-onboarding skill
Adds a skill that systematically analyzes an unfamiliar codebase and
produces two artifacts: a structured onboarding guide and a starter
CLAUDE.md tailored to the project's conventions.
Four-phase workflow:
1. Reconnaissance — parallel detection of manifests, frameworks, entry
points, directory structure, tooling, and test setup
2. Architecture mapping — tech stack, patterns, key directories, request
lifecycle tracing
3. Convention detection — naming, error handling, async patterns, git
workflow from recent history
4. Artifact generation — scannable onboarding guide + project-specific
CLAUDE.md
Includes Antigravity support via .agents/skills/ and openai.yaml.
* fix: address review feedback on codebase-onboarding skill
- Rename headings to match skill format: When to Activate → When to Use,
Onboarding Workflow → How It Works
- Add Examples section with 3 usage scenarios
- Mark Phase 4 Next.js paths as example with HTML comments
- Fix CLAUDE.md generation to read/enhance existing file first
- Replace abbreviated .agents/ SKILL.md with full copy per repo convention
* fix: add example marker to Common Tasks template section
Adds <!-- Example for a Node.js project --> comment to Common Tasks,
matching the markers already on Key Entry Points and Where to Look.
Syncs .agents/ copy.
* fix: add missing example markers and shorten default_prompt
- Add example comment to Tech Stack table in Phase 4 template
- Add example comment to Key Directories block in Phase 2
- Shorten openai.yaml default_prompt to match repo convention (~60 chars)
- Sync .agents/ SKILL.md copy
* fix: add empty-repo fallback and remove hardcoded output path
- Phase 3: add fallback for repos with no git history
- Example 1: remove hardcoded docs/ path assumption, output to
conversation or project root instead
- Sync .agents/ copy
* fix: remove .agents/ duplicate, keep canonical in skills/
* fix: clarify Example 1 output destination
* fix: add shallow-clone fallback to git conventions detection
---------
Co-authored-by: vazidmansuri005 <vazidmansuri005@users.noreply.github.com>
* feat(skills): add agent-eval for head-to-head coding agent comparison
* fix(skills): address PR #540 review feedback for agent-eval skill
- Remove duplicate "When to Use" section (kept "When to Activate")
- Add Installation section with pip install instructions
- Change origin from "community" to "ECC" per repo convention
- Add commit field to YAML task example for reproducibility
- Fix pass@k mislabeling to "pass rate across repeated runs"
- Soften worktree isolation language to "reproducibility isolation"
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Pin agent-eval install to specific commit hash
Address PR review feedback: pin the VCS install to commit
6d062a2 to avoid supply-chain risk from unpinned external deps.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Joaquin Hui Gomez <joaquinhui1995@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
In git worktrees, .git is a file (not a directory) containing a gitdir
pointer. The -d test fails for worktree checkouts, causing project
detection to fall through to the "global" fallback. Changing to -e
(exists) handles both regular repos and worktrees correctly.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The observer's Haiku subprocess cannot access files outside the project
sandbox (/tmp/ for observations, ~/.claude/homunculus/ for instincts).
Adding --allowedTools "Read,Write" grants the necessary file access
while keeping the subprocess constrained by --max-turns and timeout.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three fixes for the positive feedback loop causing runaway memory usage:
1. SIGUSR1 throttling in observe.sh: Signal observer only every 20
observations (configurable via ECC_OBSERVER_SIGNAL_EVERY_N) instead
of on every tool call. Uses a counter file to track invocations.
2. Re-entrancy guard in observer-loop.sh on_usr1(): ANALYZING flag
prevents parallel Claude analysis processes from spawning when
signals arrive while analysis is already running.
3. Cooldown + tail-based sampling in observer-loop.sh:
- 60s cooldown between analyses (ECC_OBSERVER_ANALYSIS_COOLDOWN)
- Only last 500 lines sent to LLM (ECC_OBSERVER_MAX_ANALYSIS_LINES)
instead of the entire observations file
Closes#521
* feat(continuous-learning-v2): add lazy-start observer logic
Auto-starts observer when observer.enabled: true in config and no .observer.pid exists.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(continuous-learning-v2): address PR review concerns
- Use flock for atomic check-then-act to prevent race conditions
- Check both project-scoped AND global PID files before starting
- Support CLV2_CONFIG override for config file path
- Check disabled file in lazy-start logic
- Use double-check pattern after acquiring lock
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(observe.sh): address PR review comments
- Add stale PID cleanup via _CHECK_OBSERVER_RUNNING function
- Add macOS fallback using lockfile when flock unavailable
- Fix CLV2_CONFIG override: use EFFECTIVE_CONFIG for both check and read
- Use proper Python context manager (with open() as f)
- Deduplicate signaled PIDs to avoid duplicate USR1 signals
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(observe.sh): wrap macOS lockfile fallback in subshell with trap
- Wrap lockfile block in subshell so exit 0 only terminates that block
- Add trap for EXIT to clean up lock file on script interruption
- Add -l 30 (30 second expiry) to prevent permanent lock file stuck
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(observe.sh): address remaining PR review comments
- Validate PID is a positive integer before kill calls to prevent
signaling invalid targets (e.g. -1 could signal all processes)
- Pass config path via env var instead of interpolating shell variable
into Python -c string to prevent injection/breakage on special paths
- Check CLV2_CONFIG-derived directory for disabled file so disable
guard respects the same config source as lazy-start
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* Add Claude DevFleet multi-agent orchestration skill
Adds a skill for Claude DevFleet — a multi-agent coding platform that dispatches
Claude Code agents to work on missions in parallel, each in an isolated git worktree.
The skill teaches Claude Code how to use DevFleet's 11 MCP tools to plan projects,
dispatch agents, monitor progress, and read structured reports.
Setup: claude mcp add devfleet --transport sse http://localhost:18801/mcp/sse
Repo: https://github.com/LEC-AI/claude-devfleet
* Add DevFleet MCP config and /devfleet command
- Add devfleet entry to mcp-configs/mcp-servers.json for discovery
- Add /devfleet slash command for multi-agent orchestration workflow
* Add orchestration flow diagrams to skill and command
- Add visual flow to SKILL.md showing plan → dispatch → auto-chain → report
- Add flow to /devfleet command showing the trigger sequence
* Fix review feedback: frontmatter, workflow docs, HTTP transport
- Add YAML description frontmatter to commands/devfleet.md
- Fix manual workflow in SKILL.md to capture project_id from create_project
- Change mcp-servers.json from deprecated SSE to Streamable HTTP transport
* Address all review comments
* Add monitoring/reporting steps to full auto pattern
Addresses review feedback: the full auto example now includes polling
for completion and retrieving reports, matching the other patterns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Update skills/claude-devfleet/SKILL.md
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
* Update skills/claude-devfleet/SKILL.md
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Update commands/devfleet.md
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Fix review feedback
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Avdhesh Singh Chouhan <avdhesh.acro@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* feat(skills): add team-builder skill
Interactive agent picker that dynamically discovers agent markdown files,
presents a browsable domain menu, and dispatches selected agents in parallel
on a user-defined task with synthesized results.
* fix: address PR #501 review feedback
- Support both flat and subdirectory agent layouts
- Multi-path discovery with fallback probe order
- Empty-discovery fallback with helpful error message
- Enforce 5-agent cap at selection time
- Rename sections for clarity (Process → How It Works)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve PR #501 round 2 review feedback
- Fix contradictory probe-order semantics: merge-all, not first-wins
- Fix flat-layout domain extraction: frequency-based (2+ files) heuristic
- Add multi-word domain limitation note for flat layout
- Define deterministic ordering for overflow selection (alphabetical)
- Clarify TeamCreate as Claude Code tool, not undefined reference
- Shorten description frontmatter to ~60 chars
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve PR #501 round 3 review feedback
- Flat layout example now shows 2+ files per prefix (marketing, sales)
to match the documented 2+ rule
- Add filename-based fallback when agent file has no # Heading
- Add failure handling for parallel agent spawns in Step 4
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Sebastien Tang <128077249+Sabdenrog@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Patterns for catching regressions introduced by AI coding agents.
Covers sandbox/production parity testing, API response shape
verification, and integration with bug-check workflows.
Based on real-world experience where AI (Claude Code) introduced
the same bug 4 times because the same model wrote and reviewed
the code — only automated tests caught it.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
