everything-claude-code

fix: session-scoped state to prevent cross-session race

Addresses reviewer feedback from @affaan-m:

1. State keyed by CLAUDE_SESSION_ID / ECC_SESSION_ID
   - Falls back to pid-based isolation when env vars absent
   - State file: state-{sessionId}.json (was .session_state.json)

2. Atomic write+rename semantics
   - Write to temp file, then fs.renameSync to final path
   - Prevents partial reads from concurrent hooks

3. Bounded checked list (MAX_CHECKED_ENTRIES = 500)
   - Prunes to last 500 entries when cap exceeded
   - Stale session files auto-deleted after 1 hour

9/9 tests pass.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

seto · 2026-04-13 15:30:34 +09:00

45823fcede

fix: gate MultiEdit tool alongside Edit/Write

MultiEdit was bypassing the fact-forcing gate because only Edit and
Write were checked. Now MultiEdit triggers the same edit gate (list
importers, public API, data schemas) before allowing file modifications.

Updated both the hook logic and hooks.json matcher pattern.

Addresses coderabbit/greptile/cubic-dev: "MultiEdit bypasses gate"

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

seto · 2026-04-12 18:18:16 +09:00

9a64e0d271

fix: allow destructive bash retry after facts presented

Destructive bash gate previously denied every invocation with no
isChecked call, creating an infinite deny loop. Now gates per-command
on first attempt and allows retry after the model presents the required
facts (targets, rollback plan, user instruction).

Addresses greptile P1: "Destructive bash gate permanently blocks"

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

seto · 2026-04-12 18:08:15 +09:00

b6a290d061

fix: address P2 review feedback (coderabbitai, cubic-dev-ai)

- GATEGUARD_STATE_DIR env var for test isolation (hook + tests)
- Exit code assertions on all 9 tests (no vacuous passes)
- Non-vacuous allow-path assertions (verify pass-through preserves input)
- Robust newline-injection assertion
- clearState() now reports errors instead of swallowing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

seto · 2026-04-12 18:04:09 +09:00

96139b2dad

fix: address P1 review feedback from greptile bot

1. Use run-with-flags.js wrapper (supports ECC_HOOK_PROFILE, ECC_DISABLED_HOOKS)
2. Add session timeout (30min inactivity = state reset, fixes "once ever" bug)
3. Add 9 integration tests (deny/allow/timeout/sanitize/disable)

Refactored hook to module.exports.run() pattern for direct require() by
run-with-flags.js (~50-100ms faster per invocation).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

seto · 2026-04-12 17:42:32 +09:00

8a2d13187c

feat(hooks,skills): add gateguard fact-forcing pre-action gate

A PreToolUse hook that forces Claude to investigate before editing.
Instead of self-evaluation ("are you sure?"), it demands concrete facts:
importers, public API, data schemas, user instruction.

A/B tested: +2.25 quality points (9.0 vs 6.75) across two independent tasks.

- scripts/hooks/gateguard-fact-force.js — standalone Node.js hook
- skills/gateguard/SKILL.md — skill documentation
- hooks/hooks.json — PreToolUse entries for Edit|Write and Bash

Full package with config: pip install gateguard-ai
Repo: https://github.com/zunoworks/gateguard

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

seto · 2026-04-12 11:41:33 +09:00

5a03922934

feat(ecc2): persist tool log params and trigger context

Affaan Mustafa · 2026-04-09 08:04:18 -07:00

b01a300c31

feat(ecc2): infer tracked write modifications

Affaan Mustafa · 2026-04-09 07:48:29 -07:00

31f672275e

feat(ecc2): persist file activity patch previews

Affaan Mustafa · 2026-04-09 07:45:37 -07:00

eee9768cd8

feat(ecc2): persist file activity diff previews

Affaan Mustafa · 2026-04-09 07:40:28 -07:00

c395b42d2c

feat(ecc2): classify typed file activity

Affaan Mustafa · 2026-04-09 07:33:42 -07:00

edd027edd4

feat(ecc2): sync hook activity into session metrics

Affaan Mustafa · 2026-04-09 07:02:24 -07:00

48fd68115e

feat: sync ecc2 cost tracker metrics

Affaan Mustafa · 2026-04-09 06:22:20 -07:00

08f61f667d

fix: treat oauth mcp 401 probes as reachable

Affaan Mustafa · 2026-04-08 15:34:34 -07:00

e363c54057

chore: remove legacy insaits integration

Affaan Mustafa · 2026-04-05 20:19:21 -07:00

8488811b80

fix: prune expired session files on session start

Affaan Mustafa · 2026-04-05 14:58:10 -07:00

2f0a40a63f

feat: inject active instincts into session start context

Affaan Mustafa · 2026-04-05 14:55:31 -07:00

b9d0e0b04d

fix: shorten plugin slug to ecc

Affaan Mustafa · 2026-04-05 14:31:30 -07:00

1346f83b08

fix: harden install target filtering and MCP health probes

Affaan Mustafa · 2026-04-05 13:59:42 -07:00

8baffb4ad3

fix: clean up observer sessions on lifecycle end

Affaan Mustafa · 2026-04-02 18:02:29 -07:00

16e9b17ad7

feat: add web frontend rules and design quality hook

Affaan Mustafa · 2026-04-02 17:33:17 -07:00

31c9f7c33e

fix: port safe ci cleanup from backlog

Affaan Mustafa · 2026-04-01 16:09:54 -07:00

8f63697113

fix: restore ci lockfile and hook validation

Affaan Mustafa · 2026-03-31 18:00:07 -07:00

a273c62f35

perf(hooks): batch format+typecheck at Stop instead of per Edit (#746 )

* perf(hooks): batch format+typecheck at Stop instead of per Edit

Fixes #735. The per-edit post:edit:format and post:edit:typecheck hooks
ran synchronously after every Edit call, adding 15-30s of latency per
file — up to 7.5 minutes for a 10-file refactor.

New approach:
- post-edit-accumulator.js (PostToolUse/Edit): lightweight hook that
  records each edited JS/TS path to a session-scoped temp file in
  os.tmpdir(). No formatters, no tsc — exits in microseconds.
- stop-format-typecheck.js (Stop): reads the accumulator once per
  response, groups files by project root and runs the formatter in
  one batched invocation per root, then groups .ts/.tsx files by
  tsconfig dir and runs tsc once per tsconfig. Clears the accumulator
  immediately on read so repeated Stop calls don't double-process.

For a 10-file refactor: was 10 × (15s + 30s) = 7.5 min overhead,
now 1 × (batch format + batch tsc) = ~5-30s total.

* fix(hooks): address race condition, spawn timeout, and Windows path guard

Three issues raised in code review:

1. Race condition: switched accumulator from non-atomic JSON
   read-modify-write to appendFileSync (one path per line). Concurrent
   Edit hook processes each append independently without clobbering each
   other. Deduplication moved to the Stop hook at read time.

2. Effective timeout: added run() export to stop-format-typecheck.js so
   run-with-flags.js uses the direct require() path instead of falling
   through to spawnSync (which has a hardcoded 30s cap). The 120s
   timeout in hooks.json now governs the full batch as intended.

3. Windows path guard: added spaces and parentheses to UNSAFE_PATH_CHARS
   so paths like "C:\Users\John Doe\project\file.ts" are caught before
   being passed to cmd.exe with shell: true.

* fix(hooks): fix session fallback, stale comment, trim verbose comments

- Replace 'default' session ID fallback with a cwd-based sha1 hash so
  concurrent sessions in different projects don't share the same
  accumulator file when CLAUDE_SESSION_ID is unset
- Remove stale "JSON file" reference in accumulator header (format is
  now newline-delimited plain text)
- Remove redundant/verbose inline comments throughout both files

* fix(hooks): sanitize session ID, fix Windows tsc, proportional timeouts

- Sanitize CLAUDE_SESSION_ID with /[^a-zA-Z0-9_-]/g before embedding in
  the temp filename so crafted separators or '..' sequences cannot escape
  os.tmpdir() (cubic P1)
- Fix typecheckBatch on Windows: npx.cmd requires shell:true like
  formatBatch already does; use spawnSync and extract stdout/stderr from
  the result object (coderabbit P1)
- Proportional per-batch timeouts: divide 270s budget across all format
  and typecheck batches so sequential runs in monorepos stay within the
  Stop hook wall-clock limit (greptile P2)
- Raise Stop hook timeout from 120s to 300s to give large monorepos
  adequate headroom (cubic P2)

* fix(hooks): extend accumulator to Write|MultiEdit, fix tests

- Extend matcher from Edit to Edit|Write|MultiEdit so files created with
  Write and all files in a MultiEdit batch are included in the Stop-time
  format+typecheck pass (cubic P1)
- Handle tool_input.edits[] array in accumulator for MultiEdit support
- Rename misleading 'concurrent writes' test to clarify it tests append
  preservation, not true concurrency (cubic P2)
- Add Stop hook dedup test: writes duplicate paths to accumulator and
  verifies the hook clears it cleanly (cubic P2)
- Add Write and MultiEdit accumulation tests

* fix(hooks): move timeout to command level, add dedup unit tests

- Move timeout: 300 from the matcher object to the hook command object
  where it is actually enforced; the previous position was a no-op
  (cubic P2)
- Extract parseAccumulator() and export it so tests can assert dedup
  behavior directly without relying only on side effects (cubic P2)
- Add two unit tests for parseAccumulator: deduplication and blank-line
  handling; rename the integration test to match its scope

* fix(hooks): replace removed format/typecheck hooks with accumulator in cursor adapter

Yuval Dinodia · 2026-03-31 14:12:12 -07:00

95e606fb81

fix: filter session-start injection by cwd/project to prevent cross-project contamination (#1054 )

* fix: filter session-start injection by cwd/project to prevent cross-project contamination

The SessionStart hook previously selected the most recent session file
purely by timestamp, ignoring the current working directory. This caused
Claude to receive a previous project's session context when switching
between projects, leading to incorrect file reads and project analysis.

session-end.js already writes **Project:** and **Worktree:** header
fields into each session file. This commit adds selectMatchingSession()
which uses those fields with the following priority:

1. Exact worktree (cwd) match — most recent
2. Same project name match — most recent
3. Fallback to overall most recent (preserves backward compatibility)

No new dependencies. Gracefully falls back to original behavior when
no matching session exists.

* fix: address review feedback — eliminate duplicate I/O, add null guards, improve docstrings

- Return { session, content, matchReason } from selectMatchingSession()
  to avoid reading the same file twice (coderabbitai, greptile P2)
- Add empty array guard: return null when sessions.length === 0 (coderabbitai)
- Stop mutating input objects — no more session._matchReason (coderabbitai)
- Add null check on result before accessing properties (coderabbitai)
- Only log "selected" after confirming content is readable (cubic-dev-ai P3)
- Add full JSDoc with @param/@returns (docstring coverage)

* fix: track fallback session object to prevent session/content mismatch

When sessions[0] is unreadable, fallbackContent came from a later
session (e.g. sessions[1]) while the returned session object still
pointed to sessions[0]. This caused misleading logs and injected
content from the wrong session — the exact problem this PR fixes.

Now tracks fallbackSession alongside fallbackContent so the returned
pair is always consistent.

Addresses greptile-apps P1 review feedback.

* fix: normalize worktree paths to handle symlinks and case differences

On macOS /var is a symlink to /private/var, and on Windows paths may
differ in casing (C:\repo vs c:\repo). Use fs.realpathSync() to
resolve both sides before comparison so worktree matching is reliable
across symlinked and case-insensitive filesystems.

cwd is normalized once outside the loop to avoid repeated syscalls.

Addresses coderabbitai Major review feedback.

---------

Co-authored-by: kuqili <kuqili@tencent.com>

kuqili · 2026-03-31 14:05:34 -07:00

e86d3dbe02

fix: extract inline SessionStart bootstrap to separate file (#1035 )

Inline `node -e "..."` in hooks.json contained `!` characters (e.g.
`!org.isDirectory()`) that bash history expansion in certain shell
environments would misinterpret, producing syntax errors and the
"SessionStart:startup hook error" banner in the Claude Code CLI header.

Extract the bootstrap logic to `scripts/hooks/session-start-bootstrap.js`
so the shell never sees the JS source. Behaviour is identical: the script
reads stdin, resolves the ECC plugin root via CLAUDE_PLUGIN_ROOT or a set
of well-known fallback paths, then delegates to run-with-flags.js.

Update the test that asserted the old inline pattern to verify the new
file-based approach instead.

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

Apptah · 2026-03-31 14:05:23 -07:00

30ab9e2cd7

fix(hooks): pass phase argument from hook ID to observe.sh (#1042 )

The shell wrapper run-with-flags-shell.sh was not extracting the phase
prefix from the hook ID (e.g., "pre:observe" -> "pre") and passing it
as $1 to the invoked script. This caused observe.sh to always default
to "post", recording all observations as tool_complete events with no
tool_start events captured.

Fixes #1018

Co-authored-by: Millectable <noreply@github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Mitchell · 2026-03-31 14:05:16 -07:00

5596159a83

feat(hooks): add WSL desktop notification support via PowerShell + BurntToast (#1019 )

* fix(hooks): add WSL desktop notification support via PowerShell + BurntToast

Adds WSL (Windows Subsystem for Linux) desktop notification support to the
existing desktop-notify hook. The hook now detects WSL, finds available
PowerShell (7 or Windows PowerShell), checks for BurntToast module, and
sends Windows toast notifications.

New functions:
- isWSL(): detects WSL environment
- findPowerShell(): finds PowerShell 7 or Windows PowerShell on WSL
- isBurntToastAvailable(): checks if BurntToast module is installed
- notifyWindows(): sends Windows toast notification via BurntToast

If BurntToast is not installed, logs helpful tip for installation.
Falls back silently on non-WSL/non-macOS platforms.

* docs(hooks): update desktop-notify description to include WSL

Updates the hook description in hooks.json to reflect the newly
added WSL notification support alongside macOS.

* fix(hooks): capture stderr properly in notifyWindows

Change stdio to ['ignore', 'pipe', 'pipe'] so stderr is captured
and can be logged on errors. Without this, result.stderr is null
and error logs show 'undefined' instead of the actual error.

* fix(hooks): quote PowerShell path in install tip for shell safety

The PowerShell path contains spaces and needs to be quoted
when displayed as a copy-pasteable command.

* fix(hooks): remove external repo URL from tip message

BurntToast module is a well-known Microsoft module but per project
policy avoiding unvetted external links in user-facing output.

* fix(hooks): probe WSL interop PATH before hardcoded paths

Adds 'pwsh.exe' and 'powershell.exe' as candidates to leverage
WSL's Windows interop PATH resolution, making the hook work with
non-default WSL mount prefixes or Windows drives.

* perf(hooks): memoize isWSL detection at module load

Avoids reading /proc/version twice (once in run(), once in findPowerShell())
by computing the result once when the module loads.

* perf(hooks): reduce PowerShell spawns from 3 to 1 per notification

Merge findPowerShell version check and isBurntToastAvailable check
into a single notifyWindows call. Now just tries to send directly;
if it fails, tries next PowerShell path. Version field was unused.

Net effect: up to 3 spawns reduced to 1 in the happy path.

* fix(hooks): remove duplicate notifyWindows declaration

There were two notifyWindows function declarations due to incomplete
refactoring. Keeps only the version that returns true/false for the
call site. Node.js would throw SyntaxError with 'use strict'.

* fix(hooks): improve error handling and detection robustness

- Increase PowerShell detection timeout from 1s to 3s to avoid false
  negatives on slower/cold WSL interop startup
- Return error reason from notifyWindows to distinguish BurntToast
  module not found vs other PowerShell errors
- Log actionable error details instead of always showing install tip

---------

Co-authored-by: boss <boss@example.com>

QWsin · 2026-03-30 03:14:49 -04:00

118e57e14b

fix: narrow unicode cleanup scope

Affaan Mustafa · 2026-03-29 21:21:18 -04:00

7483d646e4

fix: harden unicode safety checks

Affaan Mustafa · 2026-03-29 21:21:18 -04:00

866d9ebb53

Merge branch 'main' into fix/doc-file-warning-denylist

Affaan Mustafa · 2026-03-29 00:13:48 -04:00

f2bf72c005

fix(hooks): make pre-commit quality checks enforce staged state

Affaan Mustafa · 2026-03-29 00:07:18 -04:00

81acf0c928

fix(lint): prefix unused options parameter with underscore

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-29 10:14:53 +08:00

7462168377

refactor: address reviewer feedback

- Add options={} parameter to run() to match run-with-flags.js contract
- Remove case-insensitive flag from extension pre-filter for consistency
  with ADHOC_FILENAMES regex (both now case-sensitive)
- Expand warning text to list more structured paths
- Add test cases for uppercase extensions (TODO.MD, NOTES.TXT)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-29 10:09:02 +08:00

3c3781ca43

fix(hooks): port doc-file-warning denylist policy to current hook runtime

Replace the broad allowlist approach with a targeted denylist that only
warns on known ad-hoc filenames (NOTES, TODO, SCRATCH, TEMP, DRAFT,
BRAINSTORM, SPIKE, DEBUG, WIP) outside structured directories. This
eliminates false positives for legitimate markdown-heavy workflows while
still catching impulse documentation files.

Closes #988

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-29 09:54:23 +08:00

27d71c9548

feat(hooks): add pre-commit quality check hook

- Add pre-bash-commit-quality.js hook script
- Runs quality checks before git commit commands:
  - Lints staged files (ESLint, Pylint, golint)
  - Validates commit message format (conventional commits)
  - Detects console.log/debugger statements
  - Warns about TODO/FIXME without issue references
  - Detects potential hardcoded secrets
- Updates hooks.json with new hook configuration
- Updates README.md with hook documentation

Cross-platform (Windows, macOS, Linux)

xingzihai · 2026-03-26 00:28:26 +00:00

b44ba7096f

Merge pull request #846 from pythonstrup/feat/desktop-notify-hook

feat: add macOS desktop notification Stop hook

Affaan Mustafa · 2026-03-25 03:19:13 -07:00

678fb6f0d3

fix: finish blocker lane hook and install regressions

Affaan Mustafa · 2026-03-25 04:00:50 -04:00

b19b4c6b5e

fix: finish hook fallback and canonical session follow-ups

Affaan Mustafa · 2026-03-25 03:44:03 -04:00

9c5ca92e6e

fix: add spawnSync error logging and restore 5s timeout

- Check spawnSync result and log warning on failure via stderr
- Restore osascript timeout to 5000ms, increase hook deadline to 10s
  for sufficient headroom

Jonghyeok Park · 2026-03-25 16:03:21 +09:00

f6b10481f3

fix: use AppleScript-safe escaping and reduce spawnSync timeout

- Replace JSON.stringify with curly quote substitution for AppleScript
  compatibility (AppleScript does not support \" backslash escapes)
- Reduce spawnSync timeout from 5000ms to 3000ms to leave headroom
  within the 5s hook deadline

Jonghyeok Park · 2026-03-25 16:03:21 +09:00

d3699f9010

feat: add macOS desktop notification Stop hook

Add a new Stop hook that sends a native macOS notification with the
task summary (first line of last_assistant_message) when Claude finishes
responding. Uses osascript via spawnSync for shell injection safety.
Supports run-with-flags fast require() path. Only active on standard
and strict profiles; silently skips on non-macOS platforms.

Jonghyeok Park · 2026-03-25 16:03:21 +09:00

445ae5099d

fix: fold session manager blockers into one candidate

Affaan Mustafa · 2026-03-24 23:08:27 -04:00

1d0aa5ac2a

feat(hooks): add config protection hook to block linter config manipulation (#758 )

* 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.

Charlie Tonneslan · 2026-03-22 15:39:54 -07:00

fdb10ba116

feat: add MCP health-check hook (#711 )

Affaan Mustafa · 2026-03-20 05:56:21 -07:00

e8495aa3fc

fix: sanitize SessionStart session summaries (#710 )

Affaan Mustafa · 2026-03-20 05:42:32 -07:00

35071150b7

feat: agent compression, inspection logic, governance hooks (#491 , #485 , #482 ) (#688 )

Implements three roadmap features:

- Agent description compression (#491): New `agent-compress` module with
  catalog/summary/full compression modes and lazy-loading. Reduces ~26k
  token agent descriptions to ~2-3k catalog entries for context efficiency.

- Inspection logic (#485): New `inspection` module that detects recurring
  failure patterns in skill_runs. Groups by skill + normalized failure
  reason, generates structured reports with suggested remediation actions.
  Configurable threshold (default: 3 failures).

- Governance event capture hook (#482): PreToolUse/PostToolUse hook that
  detects secrets, policy violations, approval-required commands, and
  elevated privilege usage. Gated behind ECC_GOVERNANCE_CAPTURE=1 flag.
  Writes to governance_events table via JSON-line stderr output.

59 new tests (16 + 16 + 27), all passing.

Affaan Mustafa · 2026-03-20 01:38:13 -07:00

0b0b66c02f

fix: strip ANSI escape codes from session persistence hooks (#642 ) (#684 )

Windows terminals emit control sequences (cursor movement, screen
clearing) that leaked into session.tmp files and were injected
verbatim into Claude's context on the next session start.

Add a comprehensive stripAnsi() to utils.js that handles CSI, OSC,
charset selection, and bare ESC sequences. Apply it in session-end.js
(when extracting user messages from the transcript) and in
session-start.js (safety net before injecting session content).

Affaan Mustafa · 2026-03-20 01:38:11 -07:00

28de7cc420

fix: export run() to avoid Windows spawnSync issues (#431 )

- session-end-marker.js now exports run() function
- Enables in-process execution via run-with-flags.js
- Avoids spawnSync cross-platform issues on Windows
- Maintains backward compatibility with direct CLI execution

Fixes #429

Co-authored-by: 阳虎 <yanghu@yanghudeMacBook-Pro.local>

yang1002378395-cmyk · 2026-03-16 13:38:47 -07:00

9fcbe9751c

feat: add orchestration workflows and harness skills

Affaan Mustafa · 2026-03-12 14:49:05 -07:00

4d4ba25d11

112 Commits