Changes based on CodeRabbit review feedback:
1. Remove entire .cursor/ directory — it was an identical copy of the
main skills/commands/agents/rules, causing maintenance drift.
Users of Cursor can reference the canonical files directly.
2. Use explicit `is not None` checks instead of truthiness for
parsed['input'] and parsed['output']. Empty strings or empty
dicts are valid values that should be preserved.
The observe.sh script receives "pre" or "post" as $1 from the hook
config, but the Python code was looking for a "hook_type" field in
the stdin JSON. Claude Code does NOT include "hook_type" in the
JSON payload passed to hooks, so it always defaulted to "unknown",
causing all observations to be recorded as "tool_complete" —
PreToolUse events were never distinguished from PostToolUse.
Fix: capture $1 as HOOK_PHASE and pass it to Python via env var.
This also fixes TIMESTAMP export in the .cursor copy where inline
`VAR=val cmd` syntax didn't propagate to the python subprocess.
Fix ItemListView to accept viewModel via init with default parameter
so previews can inject mocks. Fix ExpensiveChartView Equatable to
compare full array instead of only count.
The inline environment variable syntax `TIMESTAMP="$timestamp" echo ...`
does not work correctly because:
1. The pipe creates a subshell that doesn't inherit the variable
2. The environment variable is set for echo, not for the piped python
Fixed by using `export` and separating the commands:
- export TIMESTAMP="$timestamp"
- echo "$INPUT_JSON" | python3 -c "..."
This ensures the TIMESTAMP variable is available to the python subprocess.
Fixes#227
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The observer agent creates instinct files as .md with YAML frontmatter,
but load_all_instincts() only globbed *.yaml and *.yml. Add *.md to the
glob so instinct-cli status discovers all instinct files.
- Load both .yaml and .yml files in load_all_instincts() (#216)
The *.yaml-only glob missed .yml files, causing 'No instincts found'
- Implement evolve --generate to create skill/command/agent files (#217)
Previously printed a stub message. Now generates SKILL.md, command .md,
and agent .md files from the clustering analysis into ~/.claude/homunculus/evolved/
Docker Compose for local dev, networking, volume strategies, container
security hardening, debugging commands, and anti-patterns.
Complements the existing deployment-patterns skill which covers CI/CD
and production Dockerfiles.
Closes#121
Integration tests were still passing CLAUDE_TRANSCRIPT_PATH as an env
var, but evaluate-session.js now reads transcript_path from stdin JSON.
Also improves strategic-compact skill with decision guide and survival table.
- Migrate session-end.js and evaluate-session.js from CLAUDE_TRANSCRIPT_PATH
env var to stdin JSON transcript_path (correct hook input mechanism)
- Remove duplicate main() calls that ran before stdin was read, causing
session files to be created with empty data
- Add range validation (1-10000) on COMPACT_THRESHOLD in suggest-compact.js
to prevent negative or absurdly large thresholds
- Add integration/hooks.test.js to tests/run-all.js so CI runs all 97 tests
- Update evaluate-session.sh to parse transcript_path from stdin JSON
- Update hooks.test.js to pass transcript_path via stdin instead of env var
- Sync .cursor/ copies
- New skills: api-design, database-migrations, deployment-patterns
- validate-hooks.js: validate inline JS syntax in node -e hook commands
- utils.test.js: edge case tests for findFiles with null/undefined inputs
- README: update skill count to 35, add new skills to directory tree
- Add try-catch around readFileSync in validate-agents, validate-commands,
validate-skills to handle TOCTOU races and file read errors
- Add validate-hooks.js and all test suites to package.json test script
(was only running 4/5 validators and 0/4 test files)
- Fix shell variable injection in observe.sh: use os.environ instead of
interpolating $timestamp/$OBSERVATIONS_FILE into Python string literals
- Fix $? always being 0 in start-observer.sh: capture exit code before
conditional since `if !` inverts the status
- Add OLD_VERSION validation in release.sh and use pipe delimiter in sed
to avoid issues with slash-containing values
- Add jq dependency check in evaluate-session.sh before parsing config
- Sync .cursor/ copies of all modified shell scripts
Core library fixes:
- session-manager.js: wrap all statSync calls in try-catch to prevent
TOCTOU crashes when files are deleted between readdir and stat
- session-manager.js: use birthtime||ctime fallback for Linux compat
- session-manager.js: remove redundant existsSync before readFile
- utils.js: fix findFiles TOCTOU race on statSync inside readdir loop
Hook improvements:
- Add 1MB stdin buffer limits to all PostToolUse hooks to prevent
unbounded memory growth from large payloads
- suggest-compact.js: use fd-based atomic read+write for counter file
to reduce race window between concurrent invocations
- session-end.js: log when transcript file is missing, check
replaceInFile return value for failed timestamp updates
- start-observer.sh: log claude CLI failures instead of silently
swallowing them, check observations file exists before analysis
Test fixes:
- Fix blocking hook tests to send matching input (dev server command)
and expect correct exit code 2 instead of 1
- Sync .cursor/observe.sh with corrected main version (use stdin pipe
instead of broken heredoc json.loads pattern)
- Fix suggest-compact.sh to use CLAUDE_SESSION_ID instead of $$ which
gives a new PID per invocation, preventing counter from incrementing
* fix: resolve multiple reported issues (#205, #182, #188, #172, #173)
- fix(observe.sh): replace triple-quote JSON parsing with stdin pipe to
prevent ~49% parse failures on payloads with quotes/backslashes/unicode
- fix(hooks.json): correct matcher syntax to use simple tool name regexes
instead of unsupported logical expressions; move command/path filtering
into hook scripts; use exit code 2 for blocking hooks
- fix(skills): quote YAML descriptions containing colons in 3 skill files
and add missing frontmatter to 2 skill files for Codex CLI compatibility
- feat(rules): add paths: filters to all 15 language-specific rule files
so they only load when working on matching file types
- fix(agents): align model fields with CONTRIBUTING.md recommendations
(opus for planner/architect, sonnet for reviewers/workers, haiku for
doc-updater)
* ci: use AgentShield GitHub Action instead of npx
Switch from npx ecc-agentshield to uses: affaan-m/agentshield@v1
for proper GitHub Action demo and marketplace visibility.
New skill: /security-scan wraps ecc-agentshield to audit .claude/ configs
for vulnerabilities, misconfigs, and injection risks.
Covers: CLAUDE.md secrets, settings.json permissions, MCP server risks,
hook injection, agent tool restrictions. Produces A-F security grade.
Also adds AgentShield section to Ecosystem Tools in README with
links to GitHub repo and npm package.
- Remove trailing whitespace from inline code
- Add blank line before table
- Fix heading levels to ensure proper hierarchy
- Convert bare URLs to markdown links
parse_instinct_file() was appending the instinct and resetting state
when frontmatter ended (second ---), before any content lines could be
collected. This caused all content (Action, Evidence, Examples) to be
lost during import.
Fix: only set in_frontmatter=False when frontmatter ends. The existing
logic at the start of next frontmatter (or EOF) correctly appends the
instinct with its collected content.
Fixes#148
Add a new skill that guides users through selective installation of
ECC skills and rules via AskUserQuestion. Clones the repo to /tmp,
lets users choose components and install level (user/project), verifies
path correctness, offers optimization, and cleans up on completion.
Co-authored-by: Hor1zonZzz <Hor1zonZzz@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
