Salvages the useful parts of #1897 without generated .caliber state or stale counts.
- adds a deterministic command registry generator and drift check
- commits the current command registry for 75 commands
- validates the rc.1 README catalog summary against live counts
- adds a single Ubuntu Node 20 coverage job instead of running coverage in every matrix cell
Co-authored-by: jodunk <jodunk@users.noreply.github.com>
Make the ECC 2.0 GitHub/Linear/handoff/roadmap progress-sync model part of the local observability readiness gate instead of leaving it as roadmap prose only.
- add `docs/architecture/progress-sync-contract.md` for GitHub, Linear, handoff, roadmap, and work-items sync
- add a `Tracker Sync` check to `scripts/observability-readiness.js`
- update observability tests with passing and missing-contract coverage
- update observability and GA roadmap docs so the local readiness gate is now 18/18 and records #1848 supply-chain hardening evidence
Validation:
- node tests/scripts/observability-readiness.test.js (9 passed, 0 failed)
- npm run observability:ready -- --format json (18/18, ready true)
- npx markdownlint-cli 'docs/architecture/progress-sync-contract.md' 'docs/architecture/observability-readiness.md' 'docs/ECC-2.0-GA-ROADMAP.md'
- git diff --check
- node tests/docs/ecc2-release-surface.test.js (18 passed)
- node tests/run-all.js (2378 passed, 0 failed)
- GitHub CI for #1849 green across Ubuntu, Windows, and macOS
No release, tag, npm publish, plugin tag, marketplace submission, or announcement was performed.
Add a repo-level supply-chain incident response playbook for npm/GitHub Actions package-registry incidents, anchored on the May 2026 TanStack compromise and prior Shai-Hulud-style npm incidents.
- add `docs/security/supply-chain-incident-response.md` with exposure checks, immediate response steps, workflow rules, publication rules, and escalation triggers
- link the playbook from `SECURITY.md`
- reject `pull_request_target` workflows that restore or save shared dependency caches
- add a regression test for the new `pull_request_target + actions/cache` guardrail
Validation:
- node tests/ci/validate-workflow-security.test.js (12 passed, 0 failed)
- node scripts/ci/validate-workflow-security.js (validated 7 workflow files)
- npx markdownlint-cli 'SECURITY.md' 'docs/security/supply-chain-incident-response.md'
- npx markdownlint-cli '**/*.md' --ignore node_modules
- git diff --check
- node tests/run-all.js (2377 passed, 0 failed)
- GitHub CI for #1848 green across Ubuntu, Windows, and macOS
No release, tag, npm publish, plugin tag, marketplace submission, or announcement was performed.
Require npm registry signature verification wherever workflow npm audit checks run.
- add npm audit signatures to CI Security Scan and maintenance security audit jobs
- teach the workflow security validator to reject npm audit without signature verification
- keep the repair and Copilot prompt tests portable across Windows path/case and CRLF frontmatter behavior
Validation:
- node tests/run-all.js (2376 passed, 0 failed)
- CI current-head matrix green on #1846
Adds GitHub Copilot VS Code instruction and prompt files for ECC workflows, with VS Code prompt frontmatter/settings aligned to current docs and tests covering the surface.
Co-authored-by: Girish Kanjiyani <girish.kanjiyani5040@gmail.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Backport Jamkris's fix for case-insensitive core.hooksPath overrides and the git commit -tn template-path false positive. Verified locally on current main with 25/25 block-no-verify tests and node tests/run-all.js passing 2369/2369.
- run non-test workflow installs with npm ci --ignore-scripts where lifecycle scripts are not needed\n- reject plain npm ci in workflows with write permissions\n- reject actions/cache in id-token: write workflows to reduce OIDC publish cache-poisoning risk
Salvages the useful statusline/context monitor work from stale PR #1504 while preserving the current continuous-learning hook runner wiring.
Adds the metrics bridge, context monitor, statusline script, shared cost/session bridge utilities, and tests. Fixes the reviewed false loop-detection hash collision for non-file tools, avoids default-session cost inflation, sanitizes statusline task lookup, and records hook payload session IDs in cost-tracker.
- add Vite and Redis pattern skills from closed stale PRs
- add frontend-slides support assets
- port skill-comply runner fixes and LLM prompt/provider regressions
- harden agent frontmatter validation and sync catalog counts
* fix(ci): flag SKILL.md frontmatter defects in validate-skills
Issue #1663 reported two SKILL.md frontmatter defects (missing `name:`
on skill-stocktake; literal block-scalar `description: |-` on
openclaw-persona-forge) that PR #1664 addresses at the data level.
This change is complementary: it extends `scripts/ci/validate-skills.js`
to catch the same class of defect statically going forward, so the
frontmatter-vs-renderer problems do not silently reappear as new skills
land.
## Checks added
- Frontmatter must declare a `name:` field.
- Frontmatter `description:` must not use a literal block scalar
(`|` / `|-` / `|+`) — these preserve internal newlines and break
flat-table renderers keyed off `description`. Folded (`>`) and inline
strings are accepted.
## Behavior
- Frontmatter findings default to WARN (exit 0) so this PR does not
break CI while the two known offenders are still on main. Pass
`--strict` or set `CI_STRICT_SKILLS=1` to promote them to ERROR
(exit 1). Structural findings (missing / empty SKILL.md) remain
errors as before.
- Today against main, the validator reports exactly two warnings —
the same two files called out in #1663 — and exits 0. When #1664
lands, the validator reports zero warnings, at which point strict
mode can be enabled in CI.
## Parser notes
- Bespoke frontmatter parser mirrors the style of `validate-agents.js`
(tolerant of UTF-8 BOM and CRLF; no new npm dependency).
- Block-scalar continuation lines are skipped so keys inside a block
scalar are not mistaken for top-level keys.
- Hidden directories (`.something/`) under skills/ are now skipped.
## Tests
Adds five focused tests to `tests/ci/validators.test.js`:
- warns when frontmatter is missing `name` (default mode)
- errors when frontmatter is missing `name` (--strict mode)
- warns on literal block-scalar description (|-)
- accepts folded (>) and inline descriptions under --strict
- skips hidden directories under skills/
## Docs
Adds two bullets to the `Skill Checklist` in CONTRIBUTING.md covering
the two rules now surfaced by the validator.
Refs #1663. Complements (does not compete with) #1664.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(ci): harden SKILL.md frontmatter checks after bot review
Address findings from CodeRabbit, Greptile, and cubic on #1669:
- Guard empty or whitespace-only `name:` values. Previously
`name: ` silently passed because the presence check only
tested key-set membership; now inspectFrontmatter captures
trimmed values and validate flags an explicit 'name is empty'
WARN/ERROR.
- Broaden block-scalar detection to cover YAML 1.2 indent
indicators (`|2`, `|-2`, `>2-`) and trailing comments
(`|- # note`). The old regex required a bare `|`/`>` with
optional `+`/`-`, which let valid-but-disallowed forms slip
through.
- Update CONTRIBUTING.md checklist to list `|+` alongside `|`
and `|-` for parity with the validator.
- Extend runSkillsValidator to accept env overrides and add four
regression tests: empty name, |+ description, |-2 + comment, and
CI_STRICT_SKILLS=1.
* fix(ci): address round-2 review on validate-skills frontmatter
- Tighten extractFrontmatter closing delimiter to require a newline or
end-of-file after the closing `---`, so body lines beginning with
`---text` are not parsed as frontmatter (CodeRabbit).
- Strip both trailing and comment-only values in inspectFrontmatter, so
`name: # todo` is surfaced as empty rather than silently passing
(cubic P2).
- Extract validateSkillDir helper so the per-directory validation
block moves out of validateSkills, keeping both functions under the
50-line guideline (CodeRabbit nit).
- Hoist runSkillsValidator to module scope in the test harness and
share the spawnSync import with execFileSync so the helper stops
re-requiring child_process on every invocation (CodeRabbit nit).
- Add regression tests: comment-only `name:` values must fail strict
mode; `---trailing` body lines must not be parsed as frontmatter.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Update tests/ci/validators.test.js
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
* fix(hooks): resolve MCP health-check spawn ENOENT on Windows
On Windows, commands like 'npx' are batch files (npx.cmd) that require
shell expansion to resolve via PATH. Without shell: true, Node.js
spawn() fails with ENOENT.
However, absolute paths (e.g. C:\Program Files\nodejs\node.exe) must
NOT use shell mode because cmd.exe misparses paths containing spaces.
Fix: enable shell mode only for non-absolute commands on Windows, using
path.isAbsolute() to distinguish. This matches how attemptReconnect()
already handles the shell option.
Fixes#1455
* fix(hooks): harden Windows shell spawn — validate command for metacharacters
Addresses bot review feedback on PR #1456:
- Add UNSAFE_SHELL_CHARS regex to guard against shell injection when
needsShell=true: cmd.exe operators (&, |, <, >, ^, %, !, (), ;,
whitespace) are rejected before shell mode is enabled
- Add typeof command === 'string' check so path.isAbsolute() cannot
throw on malformed non-string command values
- Rename test to 'via PATH resolution' (not Windows-only; runs all platforms)
- Fix misleading test comment: 'node' resolves via PATH like npx.cmd but
does not itself use .cmd; comment now accurately reflects the intent
* fix(hooks): kill full process tree on Windows when shell mode is used
When needsShell=true, the spawned child is cmd.exe. Calling child.kill()
only terminates the shell, leaving the real server process orphaned.
Use taskkill /PID <pid> /T /F on Windows+shell to kill the entire
process tree rooted at cmd.exe. Fall back to SIGTERM+SIGKILL on all
other platforms or when shell mode is not active.
* fix(hooks): fall back to child.kill() when taskkill fails
Windows taskkill can fail if it's not on PATH, the process already
exited, or permissions are denied. Previously the failure was silently
ignored and no kill signal reached the child.
Now: capture the spawnSync result and fall back to child.kill('SIGKILL')
on any taskkill error or non-zero status. This still may leak a
detached server process but at least guarantees the cmd.exe shell is
signaled.
The SessionStart hook injects the most recent *-session.tmp as
additionalContext labelled only with 'Previous session summary:'.
After a /compact boundary, the model frequently re-executes stale
slash-skill invocations it finds inside that summary, re-running
ARGUMENTS-bearing skills (e.g. /fw-task-new, /fw-raise-pr) with the
last ARGUMENTS they saw.
Observed on claude-opus-4-7 with ECC v1.9.0 on a firmware project:
after compaction resume, the model spontaneously re-enters the prior
skill with stale ARGUMENTS, duplicating GitHub issues, Notion tasks,
and branches for work that is already merged.
ECC cannot fix Claude Code's skill-state replay across compactions,
but it can stop amplifying it. Wrap the injected summary in an
explicit HISTORICAL REFERENCE ONLY preamble with a STALE-BY-DEFAULT
contract and delimit the block with BEGIN/END markers so the model
treats everything inside as frozen reference material.
Tests: update the two hooks.test.js cases that asserted on the old
'Previous session summary' literal to assert on the new guard
preamble, the STALE-BY-DEFAULT contract, and both delimiters. 219/219
tests pass locally.
Tracked at: #1534
* fix(gateguard): rewrite routineBashMsg to use fact-presentation pattern
The imperative 'Quote user's instruction verbatim. Then retry.' phrasing
triggers Claude Code's runtime anti-prompt-injection filter, deadlocking
the first Bash call of every session. The sibling gates (edit, write,
destructive) use multi-point fact-list framing that the runtime accepts.
Align routineBashMsg with that pattern to restore the gate's intended
behavior without changing run(), state schema, or any public API.
Closes#1530
* docs(gateguard): sync SKILL.md routine gate spec with new message format
CodeRabbit flagged that skills/gateguard/SKILL.md still described the
pre-fix imperative message. Update the Routine Bash Gate section to
match the numbered fact-list format used by the new routineBashMsg().
Fixes#1469.
On Windows the `claude` binary installed via `npm i -g @anthropic-ai/claude-code`
is `claude.cmd`, and Node's spawn() cannot resolve .cmd wrappers via PATH
without shell: true. The call failed with `spawn claude ENOENT` and claw.js
returned an error string to the caller.
Mirrors the fix pattern applied in PR #1456 for the MCP health-check hook.
'claude' is a hardcoded literal (not user input), so enabling shell on Windows
only is safe.
Previously the env fallback ran only when JSON.parse threw. If stdin was valid
JSON but omitted transcript_path or provided a non-string/empty value, the
script dropped to the getSessionIdShort() fallback path, re-introducing the
collision this PR targets.
Validate the parsed transcript_path and apply the env-var fallback for any
unusable value, not just malformed JSON. Matches coderabbit's outside-diff
suggestion and keeps both input-source paths equivalent.
Refs #1494
- Route the transcript-derived shortId through sanitizeSessionId so the
fallback and transcript branches remain byte-for-byte equivalent for any
non-UUID session IDs that still land in CLAUDE_SESSION_ID (greptile P1).
- Clarify the inline comment in the first regression test: clearing
CLAUDE_SESSION_ID exercises the transcript_path branch, not the
getSessionIdShort() fallback (coderabbit P2).
Refs #1494
- Use last-8 chars of transcript UUID instead of first-8, matching
getSessionIdShort()'s .slice(-8) convention. Same session now produces the
same filename whether shortId comes from CLAUDE_SESSION_ID or transcript_path,
so existing .tmp files are not orphaned on upgrade.
- Normalize extracted hex prefix to lowercase to avoid case-driven filename
divergence from sanitizeSessionId()'s lowercase output.
- Explicitly clear CLAUDE_SESSION_ID in the first regression test so the env
leak from parent test runs cannot hide the fallback path.
- Add regression tests for the lowercase-normalization path and for the case
where CLAUDE_SESSION_ID and transcript_path refer to the same UUID (backward
compat guarantee).
Refs #1494
When session-end.js runs and CLAUDE_SESSION_ID is unset, getSessionIdShort()
falls back to the project/worktree name. If any other Stop-hook in the chain
spawns a claude subprocess (e.g. an AI-summary generator using 'claude -p'),
the subprocess also fires the full Stop chain and writes to the same project-
name-based filename, clobbering the parent's valid session summary with a
summary of the summarization prompt itself.
Fix: when stdin JSON (or CLAUDE_TRANSCRIPT_PATH) provides a transcript_path,
extract the first 8 hex chars of the session UUID from the filename and use
that as shortId. Falls back to the original getSessionIdShort() when no
transcript_path is available, so existing behavior is preserved for all
callers that do not set it.
Adds a regression test in tests/hooks/hooks.test.js.
Refs #1494
`findPluginInstall()` in `scripts/harness-audit.js` scans two candidate
roots:
{rootDir}/.claude/plugins/
{HOME}/.claude/plugins/
Current Claude Code marketplace installs live one directory deeper:
{HOME}/.claude/plugins/marketplaces/{ecc,everything-claude-code}/...
As a result, running `node scripts/harness-audit.js repo` on any
consumer project reports `consumer-plugin-install: false` even when ECC
is fully installed via marketplace, costing 4 points from Tool Coverage.
Add the `marketplaces/` intermediate directory to `candidateRoots` so
both legacy and current install layouts are recognized. The change is
purely additive: existing candidate paths still resolve, and the new
ones only match when the marketplace layout is present.
Reproduction:
1. Install ECC via Claude Code plugin marketplace
2. cd into any consumer project
3. node ~/.claude/plugins/marketplaces/everything-claude-code/scripts/harness-audit.js repo
4. Observe consumer-plugin-install=false despite a working install
P1: Gate message asked for raw production data records — changed to
"redacted or synthetic values" to prevent sensitive data exfiltration
P2: SKILL.md description now includes MultiEdit (was missing after
MultiEdit gate was added in previous commit)
P2: Session key pruning now caps __prefixed keys at 50 to prevent
unbounded growth even in theoretical edge cases
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- isChecked() no longer calls saveState() — read-only operation
should not write to disk (was causing 3x writes per tool call)
- Test cleanup uses fs.rmSync(recursive) instead of fs.rmdirSync
which failed with ENOTEMPTY when .tmp files remained
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
P1 (cubic-dev-ai): Test process PID differs from spawned hook PID,
so test was seeding/clearing wrong state file. Fix: pass fixed
CLAUDE_SESSION_ID='gateguard-test-session' to spawned hooks.
P2 (cubic-dev-ai): Pruning checked array could evict __bash_session__
and other session keys, causing gates to re-fire mid-session. Fix:
preserve __prefixed keys during pruning, only evict file-path entries.
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
P1 bug reported by greptile-apps: MultiEdit uses toolInput.edits[].file_path,
not toolInput.file_path. The gate was silently allowing all MultiEdit calls.
Fix: separate MultiEdit into its own branch that iterates edits array
and gates on the first unchecked file_path.
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
- Add `minimal` profile so the security hook runs in all profiles
- Scope -n/--no-verify flag check to the detected subcommand region,
preventing false positives on chained commands (e.g. `git log -n 10`)
- Guard stdin listeners with `require.main === module` so require()
from run-with-flags.js does not register unnecessary listeners
- Verify subcommand token is preceded only by flags/flag-args after
"git", preventing misclassification of argument values as subcommands
- Add integration tests for block-no-verify hook
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace inline `npx block-no-verify@1.1.2` with a standalone Node.js
script routed through `run-with-flags.js`, matching every other hook.
Fixes two bugs:
1. npx inherits the project cwd and triggers EBADDEVENGINES in
pnpm-only projects that set devEngines.packageManager.onFail=error.
2. The hook bypassed run-with-flags.js so ECC_DISABLED_HOOKS had no
effect — the isHookEnabled() check never ran.
The new script replicates the full block-no-verify@1.1.2 detection
logic (--no-verify, -n shorthand for commit, core.hooksPath override)
with zero external dependencies.
Closes#1378
Fix two lint issues that cause `npm run lint` to exit non-zero:
1. README.md (MD028): Two consecutive blockquotes separated by a bare
blank line. Markdownlint treats this as one blockquote with an
illegal blank line inside. Replace the blank line with a `>`
continuation so both paragraphs stay in the same blockquote.
2. session-activity-tracker.js (eqeqeq): Three instances of `== null`
replaced with explicit `=== null || === undefined` guards to satisfy
the repo's `eqeqeq: warn` ESLint rule.
Closes#1366
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>
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>
- 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>
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>
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>
Affaan Mustafa
Affaan Mustafa
SeungHyun
Girish Kanjiyani
Divyesh Thirukonda
Gaurav Dubey
Michael
Affaan Mustafa
Vishnu Pradeep
Junming
Taro Kawakami
S1lverline
seto
Ke Wang