* fix: Windows compatibility for hook scripts
- post-edit-format.js: add `shell: process.platform === 'win32'` to
execFileSync options so npx.cmd is resolved via cmd.exe on Windows
- post-edit-typecheck.js: same fix for tsc invocation via npx
- hooks.json: skip tmux-dependent hooks on Windows where tmux is
unavailable (dev-server blocker and long-running command reminder)
On Windows, execFileSync('npx', ...) without shell:true fails with
ENOENT because Node.js cannot directly execute .cmd files. These
hooks silently fail on all Windows installations.
The tmux hooks unconditionally block dev server commands (exit 2) or
warn about tmux on Windows where tmux is not available.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: parse Claude Code JSONL transcript format correctly
The session-end hook expected user messages at entry.content, but
Claude Code's actual JSONL format nests them at entry.message.content.
This caused all session files to be blank templates (0 user messages
despite 136+ actual entries).
- Check entry.message?.content in addition to entry.content
- Extract tool_use blocks from assistant message.content arrays
Verified with Claude Code v2.1.41 JSONL transcripts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: ddungan <sckim@mococo.co.kr>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- hooks.json: add \b word boundary anchors to dev server blocking regex
to prevent false positives matching "npm run develop", "npm run devtools" etc.
- skill-create-output.js: guard box() horizontal repeat with Math.max(0, ...)
to prevent RangeError when title exceeds container width
- Add 13 tests for setup-package-manager.js CLI argument parsing
- Add 14 tests for skill-create-output.js SkillCreateOutput class
- All 333 tests passing
- Wrap JSON.parse in try-catch for all 6 inline hooks in hooks.json
(dev-server blocker, tmux reminder, git-push reminder, doc blocker,
PR create logger, build analysis) — previously unguarded JSON.parse
would crash on empty/malformed stdin, preventing data passthrough
- Add config parse error logging to evaluate-session.js
- Fix plugin.schema.json: author can be string or {name,url} object,
add version (semver pattern), homepage, keywords, skills, agents
- Fix package-manager.schema.json: add setAt (date-time) field and
make packageManager required to match actual code behavior
- Add hooks/README.md: comprehensive hook documentation with input schema,
customization guide, 4 ready-to-use hook recipes, and cross-platform notes
- Expand planner agent with full worked example (Stripe subscriptions plan)
and sizing/phasing guidance (119 → 212 lines)
- Add Django REST API example config (DRF + Celery + pytest + Factory Boy)
- Update README directory tree with new files
Move three complex inline hooks from hooks.json into proper external
scripts in scripts/hooks/:
- post-edit-format.js: Prettier auto-formatting (was 1 minified line)
- post-edit-typecheck.js: TypeScript check (was 1 minified line with
unbounded directory traversal, now capped at 20 levels)
- post-edit-console-warn.js: console.log warnings (was 1 minified line)
Benefits:
- Readable, documented, and properly error-handled
- Testable independently via stdin
- Consistent with other hooks (all use external scripts now)
- Adds timeouts to Prettier (15s) and tsc (30s) to prevent hangs
* 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.
Fixes#78
## Problem
The Stop hook used inline JavaScript code with `node -e`, which caused
shell syntax errors on macOS/zsh due to special characters (parentheses,
braces, arrow functions) being misinterpreted by the shell.
Error message:
/bin/sh: -c: line 0: syntax error near unexpected token \`('
## Solution
- Created scripts/hooks/check-console-log.js with the hook logic
- Updated hooks/hooks.json to reference the external script
- This follows the same pattern as other hooks in the plugin
## Benefits
- Fixes shell compatibility issues across different environments
- Improves code maintainability (separate, well-documented script)
- Follows plugin's own best practices
- Makes the code easier to test and debug
## Testing
Tested on macOS with zsh - no more syntax errors.
The hook still functions correctly to detect console.log statements.
Stop hook fires after every response, SessionEnd fires only when
session actually terminates. This was causing session-end.sh and
evaluate-session.sh to run on every response instead of at session end.
Fixes issue reported by user about hooks triggering every response.
Relative paths like ./hooks/... fail when the plugin is installed
because hooks run in the project directory, not the plugin directory.
Using ${CLAUDE_PLUGIN_ROOT} ensures scripts are found regardless of
where the plugin is installed.
Fixed paths:
- hooks/strategic-compact/suggest-compact.sh
- hooks/memory-persistence/pre-compact.sh
- hooks/memory-persistence/session-start.sh
- hooks/memory-persistence/session-end.sh
- skills/continuous-learning/evaluate-session.sh
