* 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
* perf(hooks): move post-edit-format and post-edit-typecheck to strict-only
These hooks fire synchronously on every Edit call with 15-30s timeouts
each. During multi-file refactors this adds 5-10 minutes of overhead.
Moving them from standard,strict to strict-only means they won't fire
in the default profile but are still available for users who want the
extra validation.
Fixes#735
* Also update OpenCode plugin to strict-only for format/typecheck
The OpenCode plugin had the same standard,strict profile for
post:edit:format and post:edit:typecheck, so OpenCode users on the
default profile would still get the per-edit overhead.
* feat(hooks): add config protection hook to block linter config manipulation
Agents frequently modify linter/formatter configs (.eslintrc, biome.json,
.prettierrc, .ruff.toml, etc.) to make checks pass instead of fixing
the actual code.
This PreToolUse hook intercepts Write/Edit/MultiEdit calls targeting
known config files and blocks them with a steering message that directs
the agent to fix the source code instead.
Covers: ESLint, Prettier, Biome, Ruff, ShellCheck, Stylelint, and
Markdownlint configs.
Fixes#733
* Address review: fix dead code, add missing configs, export run()
- Removed pyproject.toml from PROTECTED_FILES (was dead code since
it was also in PARTIAL_CONFIG_FILES). Added comment explaining why
it's intentionally excluded.
- Removed PARTIAL_CONFIG_FILES entirely (no longer needed).
- Added missing ESLint v9 TypeScript flat configs: eslint.config.ts,
eslint.config.mts, eslint.config.cts
- Added missing Prettier ESM config: prettier.config.mjs
- Exported run() function for in-process execution via run-with-flags,
avoiding the spawnSync overhead (~50-100ms per call).
* Handle stdin truncation gracefully, log warning instead of fail-open
If stdin exceeds 1MB, the JSON would be malformed and the catch
block would silently pass through. Now we detect truncation and
log a warning. The in-process run() path is not affected.
* fix: replace bash TOML surgery with Node add-only MCP merge
The old sync script used awk/sed to remove and re-append MCP server
sections in config.toml, causing credential extraction races, duplicate
TOML tables, and 3 fragile code paths with 9 remove_section_inplace
calls each.
Replace with a Node script (scripts/codex/merge-mcp-config.js) that
uses @iarna/toml to parse the config, then appends only missing ECC
servers — preserving all existing content byte-for-byte. Warns on
config drift, supports legacy aliases (context7 → context7-mcp), and
adds --update-mcp flag for explicit refresh.
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 PR #723 review findings for Codex MCP merge
- Use package-manager abstraction (scripts/lib/package-manager.js)
instead of hardcoding pnpm — respects CLAUDE_PACKAGE_MANAGER,
lock files, and project config
- Add Yarn 1.x fallback to npx (yarn dlx unsupported in classic)
- Add missing exa server to match .codex/config.toml baseline
- Wire up findSubSections for --update-mcp nested subtable removal
(fixes Greptile P1: Object.keys only returned top-level keys)
- Fix resolvedLabel to prefer canonical entry over legacy alias
when both exist (fixes context7/context7-mcp spurious warning)
- Fix removeSectionFromText to handle inline TOML comments
- Fix dry-run + --update-mcp to show removals before early return
- Update README parity table: 4 → 7 servers, TOML-parser-based
- Add non-npm install variants to README Codex quick start
- Update package-lock.json for @iarna/toml
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 PR #723 review comments (preflight, marker validation)
- Add Node.js and merge-mcp-config.js to preflight checks so the
script fails fast before partial writes (CodeRabbit)
- Validate marker counts: require exactly 1 BEGIN + 1 END in correct
order for clean replacement (CodeRabbit)
- Corrupted markers: strip all marker lines and re-append fresh block,
preserving user content outside markers instead of overwriting
- Move MCP_MERGE_SCRIPT to preflight section, remove duplicate
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>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
* fix(install): add rust, cpp, csharp to legacy language alias map
The legacy installer compatibility layer in install-manifests.js was
missing entries for rust, cpp, and csharp — languages that have
rules/ directories and (for rust/cpp) install-components.json entries.
Running `./install.sh rust` fails with "Unknown legacy language: rust"
because LEGACY_LANGUAGE_ALIAS_TO_CANONICAL and
LEGACY_LANGUAGE_EXTRA_MODULE_IDS didn't include these languages.
Fixes the issue reported in #694 by @mpiton.
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(install): complete csharp legacy support and add resolution tests
- Add lang:csharp component to install-components.json with
framework-language module (matching cpp/rust pattern)
- Update csharp mapping in LEGACY_LANGUAGE_EXTRA_MODULE_IDS from
empty array to ['framework-language']
- Add end-to-end resolution tests for rust, cpp, and csharp verifying
framework-language module is included in resolved moduleIds
Addresses review feedback from Copilot, Greptile, CodeRabbit, and Cubic.
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>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
* Add Turkish (tr) docs and update README
Add a full set of Turkish documentation under docs/tr (agents, changelog, CLAUDE guide, contributing, code of conduct, and many agents/commands/skills/rules files). Update README to include a link to the Turkish docs and increment the supported language count from 5 to 6. This commit adds localized guidance and references to help Turkish-speaking contributors and users.
* Update docs/tr/TROUBLESHOOTING.md
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
* Update docs/tr/README.md
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
* docs(tr): fix license link and update readmes
Update Turkish docs: change license badge link to point to repository root (../../LICENSE), increment displayed language count from 5 to 6, and remove two outdated related links from docs/tr/examples/README.md to keep references accurate.
* Update docs/tr/commands/instinct-import.md
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
* Update docs/tr/commands/checkpoint.md
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
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>
The sync script previously overwrote ~/.codex/AGENTS.md on every run,
destroying any user-authored content. This adds marker-based merging
(<!-- BEGIN ECC --> / <!-- END ECC -->) so only the ECC-managed section
is replaced on subsequent runs, preserving user content outside the
markers.
Merge logic:
- No file → create with markers
- Both markers present (ordered, CRLF-safe) → replace only the ECC section
- BEGIN without END (corrupted) → full replace (backup saved)
- No markers at all → append ECC block (preserves existing content)
Also fixes:
- Symlink preservation: uses cat > instead of mv to write through symlinks
- CRLF handling: strips \r in marker detection to handle Windows-edited files
- Marker ordering: validates BEGIN appears before END, not just that both exist
The legacy heading-match heuristic was intentionally removed per council
review: any unmarked file is either user-authored (append is safe) or
legacy ECC-generated (duplicates once, deduplicates on next run via
markers). A timestamped backup is always saved before any mutation.
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>
* feat: add agent description compression with lazy loading (#491)
Agent descriptions consume ~26k tokens (121KB across 27 agents). This adds
a compression library with three modes:
- catalog: metadata only (~2-3k tokens) for agent selection
- summary: metadata + first paragraph (~4-5k tokens) for routing
- full: no compression, for when agent is invoked
Includes lazy-load function to fetch full agent body on demand.
21 tests covering parsing, compression, filtering, and real agents dir.
* fix: update JSDoc to include all stats fields in buildAgentCatalog
Add compressedBytes and mode to the documented return type, matching
the actual implementation.
* fix(tests): skip bash tests on Windows and fix USERPROFILE in resolve-ecc-root
- hooks.test.js: add SKIP_BASH guard for 8 bash-dependent tests
(detect-project.sh, observe.sh) while keeping 207 Node.js tests running
- resolve-ecc-root.test.js: add USERPROFILE to env overrides in 2
INLINE_RESOLVE tests so os.homedir() resolves correctly on Windows
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(tests): handle BOM in shebang stripping and skip worktree tests on Windows
- validators.test.js: replace regex stripShebang with character-code
approach that handles UTF-8 BOM before shebang line
- detect-project-worktree.test.js: skip entire file on Windows since
tests invoke bash scripts directly
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>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
