The Explore agent is a "Fast agent" optimized for codebase exploration,
not deep reasoning. The skill-stocktake V4 design requires holistic AI
judgment (actionability, scope fit, uniqueness, currency) which needs
the full reasoning capability of the conversation's main model.
Additionally, the Agent tool has no `model` parameter — specifying
`model: opus` was silently ignored, causing the evaluation to run on
the lightweight Explore model. This resulted in all skills receiving
"Keep" verdicts without genuine critical analysis.
Changing to `general-purpose` agent ensures evaluation runs on the
conversation's main model (e.g., Opus 4.6), enabling the holistic
judgment that V4 was designed for.
Replace the 5-dimension numeric scoring rubric with a checklist + holistic
verdict system (Save / Improve then Save / Absorb into [X] / Drop).
Key improvements:
- Explicit pre-save checklist: grep skills/ for duplicates, check MEMORY.md,
consider appending to existing skills, confirm reusability
- 4-way verdict instead of binary save/don't-save: adds "Absorb into [X]"
to prevent skill file proliferation, and "Improve then Save" for iterative
refinement
- Verdict-specific confirmation flows tailored to each outcome
- Design rationale explaining why holistic judgment outperforms numeric
scoring with modern frontier models
- Pin installation to specific commit hash (full SHA) to mitigate
supply-chain risk (cubic-dev-ai feedback)
- Add "When to Use", "How It Works", "Examples" sections to match
repo skill format conventions (coderabbitai feedback)
- Add review-before-update instructions for safe version upgrades
- Emphasize zero-runtime-risk: pure Markdown, no executable code
Claude Code sends tool output as `tool_response` in PostToolUse hook
payloads, but observe.sh only checked for `tool_output` and `output`.
This caused all observations to have empty output fields, making the
observer pipeline blind to tool results.
Adds `tool_response` as the primary field to check, with backward-
compatible fallback to the existing `tool_output` and `output` fields.
Extract BIOME_CONFIGS and PRETTIER_CONFIGS as shared constants to eliminate
duplication between PROJECT_ROOT_MARKERS and detectFormatter(). Unify the
biome/prettier branches in resolveFormatterBin() via a FORMATTER_PACKAGES
map. Remove redundant path.resolve() in quality-gate.js.
Handle Windows .cmd shim resolution via spawnSync with strict path
validation. Removes shell:true injection risk, uses strict equality,
and restores .cmd support with path injection guard.
Invoke hook scripts directly via require() when they export a
run(rawInput) function, eliminating one Node.js process spawn per
hook invocation (~50-100ms).
Includes path traversal guard, timeouts, error logging, PR review
feedback, legacy hooks guard, normalized filePath, and restored
findProjectRoot config detection with package manager support.
- Use local node_modules/.bin/biome binary instead of npx (~200-500ms savings)
- Change post-edit-format from `biome format --write` to `biome check --write`
(format + lint in one pass)
- Skip redundant biome check in quality-gate for JS/TS files already
handled by post-edit-format
- Fix quality-gate to use findProjectRoot instead of process.cwd()
- Export run() function from both hooks for direct invocation
- Update tests to match shared resolve-formatter module usage
Extract project-root discovery, formatter detection, and binary
resolution into a reusable module. Caches results per-process to
avoid redundant filesystem lookups on every Edit hook invocation.
This is the foundation for eliminating npx overhead in format hooks.
PR #344 replaced the blocking dev-server hook with auto-tmux-dev.js
which transforms commands into tmux sessions (exit 0) instead of
blocking them (exit 2). Updated 2 tests to match the new behavior.
The "Traction & Distribution" section contained internal business
context (sponsor-call checklists, partner reporting instructions)
that doesn't belong in a user-facing README.
The "Traction & Distribution" section contained internal business
context (sponsor-call checklists, partner reporting instructions)
that doesn't belong in a user-facing README. Moved to docs/business/.
* feat(CLI): Add Antigravity IDE support via `--target antigravity` flag
This Pull Request introduces `--target antigravity` support within the installation script to bridge Everything Claude Code configurations smoothly onto the Antigravity IDE ecosystem.
### Key Changes
- Modified `install.sh` to parse and act on the new `--target antigravity` CLI arg.
- **Flattened Rules Conversion**: Logic automatically copies Language-agnostic (Common/Globs) rules as well as specific language stack rules into `common-*.md` and `{lang}-*.md` structures within `.agent/rules/`.
- **Workflow & Agent Aggregation**: Commands safely fall in `.agent/workflows/`, and `agents/` alongside `skills/` components are merged into `.agent/skills/`.
- Contains overwrite warnings to ensure local customized rules aren't completely overridden without consent.
- Minor updates to `README.md` to properly document the flag addition.
* Update install.sh
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
---------
Co-authored-by: dangnd1 <dangnd1@vnpay.vn>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
* fix: auto-start development servers in tmux instead of blocking
Replace blocking PreToolUse hook that used process.exit(2) with an auto-transform hook that:
- Detects development server commands
- Wraps them in tmux with directory-based session names
- Runs server detached so Claude Code is not blocked
- Provides confirmation message with log viewing instructions
Benefits:
- Development servers no longer block Claude Code execution
- Each project gets its own tmux session (allows multiple projects)
- Logs remain accessible via 'tmux capture-pane -t <session>'
- Non-blocking: if tmux unavailable, command still runs (graceful fallback)
Implementation:
- Created scripts/hooks/auto-tmux-dev.js with transform logic
- Updated hooks.json to reference the script instead of inline node command
- Applied same fix to cached plugin version (1.4.1) for immediate effect
* fix: resolve PR #344 code review issues in auto-tmux-dev.js
Critical fixes:
- Fix variable scope: declare 'input' before try block, not inside
- Fix shell injection: sanitize sessionName and escape cmd for shell
- Replace unused execFileSync import with spawnSync
Improvements:
- Add real Windows support using cmd /k window launcher
- Add tmux availability check with graceful fallback
- Update header comment to accurately describe platform support
Test coverage:
- Valid JSON input: transforms command for respective platform
- Invalid JSON: passes through raw data unchanged
- Unsupported tools: gracefully falls back to original command
- Shell metacharacters: sanitized in sessionName, escaped in cmd
* fix: correct cmd.exe escape sequence for double quotes on Windows
Use double-quote doubling ('""') instead of backslash-escape ('\\\") for cmd.exe syntax.
Backslash escaping is Unix convention and not recognized by cmd.exe. This fixes quoted
arguments in dev server commands on Windows (e.g., 'npm run dev --filter="my-app"').
* fix(hooks): scrub secrets and harden hook security
- Scrub common secret patterns (api_key, token, password, etc.) from
observation logs before persisting to JSONL (observe.sh)
- Auto-purge observation files older than 30 days (observe.sh)
- Strip embedded credentials from git remote URLs before saving to
projects.json (detect-project.sh)
- Add command prefix allowlist to runCommand — only git, node, npx,
which, where are permitted (utils.js)
- Sanitize CLAUDE_SESSION_ID in temp file paths to prevent path
traversal (suggest-compact.js)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(hooks): address review feedback from CodeRabbit and Cubic
- Reject shell command-chaining operators (;|&`) in runCommand, strip
quoted sections before checking to avoid false positives (utils.js)
- Remove command string from blocked error message to avoid leaking
secrets (utils.js)
- Fix Python regex quoting: switch outer shell string from double to
single quotes so regex compiles correctly (observe.sh)
- Add optional auth scheme match (Bearer, Basic) to secret scrubber
regex (observe.sh)
- Scope auto-purge to current project dir and match only archived
files (observations-*.jsonl), not live queue (observe.sh)
- Add second fallback after session ID sanitization to prevent empty
string (suggest-compact.js)
- Preserve backward compatibility when credential stripping changes
project hash — detect and migrate legacy directories
(detect-project.sh)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(hooks): block $() substitution, fix Bearer redaction, add security tests
- Add $ and \n to blocked shell metacharacters in runCommand to prevent
command substitution via $(cmd) and newline injection (utils.js)
- Make auth scheme group capturing so Bearer/Basic is preserved in
redacted output instead of being silently dropped (observe.sh)
- Add 10 unit tests covering runCommand allowlist blocking (rm, curl,
bash prefixes) and metacharacter rejection (;|&`$ chaining), plus
error message leak prevention (utils.test.js)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(hooks): scrub parse-error fallback, strengthen security tests
Address remaining reviewer feedback from CodeRabbit and Cubic:
- Scrub secrets in observe.sh parse-error fallback path (was writing
raw unsanitized input to observations file)
- Remove redundant re.IGNORECASE flag ((?i) inline flag already set)
- Add inline comment documenting quote-stripping limitation trade-off
- Fix misleading test name for error-output test
- Add 5 new security tests: single-quote passthrough, mixed
quoted+unquoted metacharacters, prefix boundary (no trailing space),
npx acceptance, and newline injection
- Improve existing quoted-metacharacter test to actually exercise
quote-stripping logic
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(security): block $() and backtick inside quotes in runCommand
Shell evaluates $() and backticks inside double quotes, so checking
only the unquoted portion was insufficient. Now $ and ` are rejected
anywhere in the command string, while ; | & remain quote-aware.
Addresses CodeRabbit and Cubic review feedback on PR #348.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
