Commit Graph
166 Commits
Author SHA1 Message Date
haelyra 54f137e7a4 maint: integrate reviewed contribution #3790 2026-10-29 11:35:58 -07:00
Tomoya.FujitaandClaude Fable 5.1 aa63399ebd feat(skills): add issue-review skill and /issue-review command
Add a GitHub issue counterpart to the PR mode of /code-review. The
canonical workflow lives in skills/issue-review and walks nine phases:
fetch the issue with gh, build project context, classify type and
completeness, verify the claim against the code at HEAD, search for
duplicates and prior fixes, assess severity and decision, write a
review artifact with a draft reply, publish only on explicit flags,
and print a one-screen summary.

Issue text is treated as untrusted data: embedded instructions are
never followed, pasted code is never run, and arbitrary links are not
fetched. Writing to GitHub is opt-in via --comment or --label and the
workflow never closes, reopens, or assigns issues.

commands/issue-review.md is the thin slash-command shim. The new
structural test guards the frontmatter, required sections, phase
order, safety invariants, and registration on every surface.

Register the skill and command in package.json, agent.yaml, the
operator-workflows install module, the quick reference, the
command-agent map, and the README; regenerate the command registry
and sync catalog counts to 312 skills and 98 commands.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Signed-off-by: Tomoya.Fujita <fujita.tomoya@triorb.co.jp>
2026-10-29 09:23:41 +09:00
Gaurav Dubey dc9bb9f2d9 fix(hooks): keep inline resolver backslash-free so hooks parse on Windows
On native Windows, Claude Code runs each hook as `bash.exe -c "<command>"`
through the Windows command line. That extra unescape layer collapses the
backslashes in the WSL path conversion of the inline plugin-root resolver,
so `.replace(/\\/g,'/')` reaches node as `.replace(/\/g,'/')` and every hook
fails with `SyntaxError: missing ) after argument list`.

Build the backslash separator with String.fromCharCode(92) and split/join
instead of regex escapes, so the resolver contains no backslash. Conversion
behaviour is unchanged. Regenerate every embedded copy (hooks.json,
codex-hooks.json, commands/*.md) and refresh hooks.metadata.json
fingerprints.

Add a test that the resolver and each hook `node -e` program are
backslash-free, and run the shipped SessionStart command through bash with
backslashes collapsed the way Windows does.

Fixes #3746
2026-10-26 18:39:04 +00:00
Alan Vo 5701a4f2e1 fix: respect CLAUDE_CONFIG_DIR with WSL Windows-path conversion
(cherry picked from commit aaacbc7592)
2026-10-20 17:40:58 -04:00
ethereal49 4aa28ccac5 fix(commands): honor Codex model configuration in Santa Loop
(cherry picked from commit 2109d97b40)
2026-10-20 17:38:04 -04:00
Affaan Mustafa 8293d0da8f fix(commands): drop unrendered LITE_MODE_FLAG token from codeagent-wrapper calls (#3640)
The multi-backend, multi-frontend, multi-plan, multi-execute and multi-workflow commands were copied from ccg-workflow's command templates, which carry {{LITE_MODE_FLAG}} and {{GEMINI_MODEL_FLAG}} for that project's installer to substitute. ECC has no substitution step, so bash passed the literal token to codeagent-wrapper as a positional argument, the backend name landed in the working-directory slot, and every call exited 1. Remove the tokens from the five commands and the ja-JP, tr and zh-CN docs copies so the wrapper receives a plain --backend invocation. A regression test scans every multi-* command and translated copy for codeagent-wrapper lines that still contain a {{TEMPLATE}} token.

Fixes #3595
2026-10-19 18:41:07 -04:00
haelyra bded8387eb fix: preflight and document snapshot storage capability 2026-10-11 12:34:15 -04:00
haelyra 1ec5b328c6 fix: normalize root overrides and report unverified snapshot staging 2026-10-11 12:05:00 -04:00
haelyra 3fa6e30502 fix: preserve rollback version state and bounded runtime workflows 2026-10-11 11:45:41 -04:00
haelyra 4ce5ae0119 fix: preserve search scope and installed cache discovery 2026-10-11 10:25:44 -04:00
haelyra b582964d67 fix(commands): execute selected-profile resolvers and honor explicit audit intent 2026-10-11 03:45:45 -04:00
haelyra 6233b648f9 fix(hooks): resolve bootstrap from selected Claude config root 2026-10-11 02:03:45 -04:00
haelyra 19a96ca2bb docs(review): keep temporary-directory guidance compatible with command validation 2026-10-10 17:51:00 -04:00
haelyra 603164ae79 feat(review): integrate consent-gated independent Codex review 2026-10-10 17:47:27 -04:00
haelyra 9d09febe5d fix(skills): scope host compatibility to target projections 2026-10-10 17:44:28 -04:00
haelyra fa7f135812 fix(qwen): integrate native workflow context and quote remaining hint 2026-10-10 17:37:01 -04:00
haelyra 94ed702344 fix(commands): preserve string argument hints from PR 3472 2026-10-10 17:36:33 -04:00
Matt Van Horn e128f4398b Merge branch 'main' into cursor/skill-host-compat-ci-10d0 2026-10-10 07:09:43 -07:00
haelyra 7265b989c4 merge: preserve tested bounded Hookify carry-forward candidate 3055 2026-10-09 16:17:57 -04:00
haelyra 6139971817 merge: preserve tested token card source 3039 and synchronize catalog 2026-10-09 16:15:37 -04:00
wellkilo a50ee13cac feat: execute bounded local Hookify rules in lifecycle hooks
Carry forward PR #3055 at 92f53c4c onto ef648e01, preserving contributor attribution and current main. Focused maintainer fixes reuse shared input ceilings, preserve late root context through outer bootstrap, bound frontmatter before immutable parsing, and assert real oversized input in the limits workflow.
2026-10-09 15:59:20 -04:00
zakyirsyaad d3ad8b524c fix: quote argument-hint values that YAML parses as arrays
Three command files declared argument-hint with an unquoted flow sequence, so a
strict YAML parse yields an array instead of a string. Harnesses that validate
the field reject the whole file: Qwen Code drops the command with
'frontmatter: Expected string, received array' and the slash command silently
disappears from the catalog.

Quote all three to match the convention already used by plan-canvas.md, pr.md,
prp-pr.md, plan-prd.md and the other argument-hint declarations in commands/.
2026-10-09 10:54:29 +07:00
kenima-arcandClaude Opus 5.5 04b60e42d7 feat(astra-review): let Astra apply fixes when Fable hits its usage limit
/astra-review now runs on Opus (model: opus). Opus verifies findings,
checks every diff, and runs the tests; fixes go to a Fable subagent.
When that Agent call fails with a rate_limit / HTTP 429 API error, the
command switches to Astra for the rest of the session:

- astra-review.js --fix-findings <file> sends confirmed findings to
  Codex in a workspace-write sandbox with the review isolation intact
  (no web search, MCP disabled, user config ignored, no API keys) and
  /tmp, $TMPDIR, and the network excluded from the writable roots.
- New scripts/lib/astra-review/fix.js builds the fix prompt, validates
  the structured fix result, and formats the report.
- codex.js shares one exec runner between review and fix; the sandbox
  is allowlisted (danger-full-access is refused).
- The command snapshots git diff and untracked files before any writer
  runs, so Opus reverts only the writer's hunks and never the user's
  uncommitted work.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-08 11:44:07 +09:00
Affaan Mustafa c05b2d6614 chore: retire the Everything Claude Code name, ECC only (#3330)
* chore: retire the Everything Claude Code name, ECC only

Replace the expanded product name and the everything-claude-code slug
with ECC across READMEs, translated docs, harness folders, skills,
commands, scripts and examples. Repo URLs now point at affaan-m/ECC.

Rename repo-internal artifacts to ecc forms (ecc-conventions skill,
ecc-guardrails, ecc-research-playbook, ecc-team-config, ecc-instincts
with ecc-* ids) and update .claude/ecc-tools.json.

Legacy install ids, plugin dirs, package names and MCP prefixes stay
where existing installs resolve against them. The codex global-state
check and harness-audit repo detection accept the new name first and
the legacy one as a fallback. The Discord bot prefers ~/GitHub/ECC and
falls back to the nested legacy checkout path.

Refresh the skill-triggers registryDigest for the changed skill text.

* fix(ecc-tools): drop managed paths to the removed Claude repo skill

.claude/skills/<repo-skill>/SKILL.md was deleted in #2770 but stayed listed in
ecc-tools.json and the team config. Remove those entries and point the Claude
Code adapter at the existing .agents/skills/ecc-conventions/SKILL.md.
2026-10-01 17:50:41 -05:00
affaan-m 19c0c167f5 Merge reviewed command trigger descriptions with preserved Santa workflow
Source-PR: https://github.com/affaan-m/ECC/pull/2969
Source-Head: b23b602bae
2026-09-28 03:58:14 -04:00
affaan-m b23b602bae Merge main and preserve clarified command descriptions
Carry the contributor descriptions and matching registry entries forward
without changing command bodies, capabilities, or skill-first policy.
2026-09-28 03:24:12 -04:00
affaan-m e8cba155a8 fix: make optional reviewer dispatch clean up safely
Preserve contributor backend selection while keeping fallback prompt-free and retaining failure status through cleanup.

Source-PR: https://github.com/affaan-m/ECC/pull/2768
Source-Head: d73009bbd1
Integration-Base: d3b8a3e908
2026-09-28 00:16:09 -04:00
iyashjayesh df34108e0f Do not promise an output path the config can override
Review caught this on the previous commit, and it was right. `sync` resolves
its target as `--out` if given, otherwise `.tokenchit.json`'s `output` —
`tokenchit.svg` is that field's default, not a fixed location. Saying the bare
command "writes tokenchit.svg in the repository root" is wrong for anyone who
has configured another path.

Checked rather than assumed: a config with `output: docs/custom-card.svg` makes
the bare command report `would write docs/custom-card.svg`.

Three places said it. Step 3 now says the configured output, the flag table no
longer implies the default is fixed, and the README snippet carries a note to
use the path sync actually reported. The command's usage comment says the same.
2026-09-27 01:43:14 +05:30
iyashjayesh 036fa49779 Merge main, and raise the pinned CLI to 0.10.0
The conflicts were all counter bumps. Upstream moved 286 -> 292 skills while
staying at 94 command shims; this branch adds one of each, so the merged values
are 293 skills and 95 shims, carried across the English, Turkish and Chinese
docs. Upstream's 2.2.2 version is kept.

One line needed care and nearly went wrong: the v2.0.0 changelog entry records
"281 skills, 67 agents, 94 command shims". That 94 is a fact about a past
release, not a live counter, and a blanket substitution had rewritten it. It is
back to 94. The Discord snowflake and the Perl badge colour both contain "94"
too and are untouched.

While here, the pin was stale. It named 0.7.0, three minor versions behind, so
anyone installing through this skill got a tool without Gemini support, the
read-only doctor report, PNG export or the portable ledger. Raised to 0.10.0 —
knowingly, which is what the skill's own note asks for — and the documented
`npm view @tokenchit/cli@0.10.0 dist.integrity dist.tarball` was run to confirm
it resolves.

The agent list was stale for the same reason: Gemini CLI became a real adapter
in 0.9.0 and the skill still advertised three agents. Verified against the
published 0.10.0 tarball rather than from memory — `init --help` and `doctor`
both name Claude Code, Codex, Gemini CLI and OpenCode.
2026-09-27 01:19:05 +05:30
Matt Van Horn da5757b6ff fix(ci): flag CLAUDE_PROJECT_DIR in skill fences with Codex rewrite guidance 2026-09-25 06:44:12 -07:00
Cursor AgentandMatt Van Horn 0895f0d8b5 feat(ci): lint skills for Codex-safe frontmatter and Claude substitutions
Add scripts/ci/validate-skill-host-compat.js and run it from the Validate
Components job and npm test after validate-skills.js. The check fails on
Claude-only substitutions in bash fences and on Codex copies that use keys
outside name, description, metadata, license, and allowed-tools. CONTRIBUTING
checklist items warn unless --strict-checklist.

Also add /skill-host-compat and skills/skill-host-compat with a Codex copy
that drops origin. Move configure-ecc plugin-root examples into prose so the
live catalog stays green without a skip list.

Co-authored-by: Matt Van Horn <mvanhorn@users.noreply.github.com>
2026-09-20 16:17:20 +00:00
kenima-arcandClaude Fable 5.1 f81a375de9 docs(astra-review): add usage guide in English and Japanese
Full manual for /astra-review: setup (Codex CLI, ChatGPT login, plugin
freshness), scopes, script options and exit codes, verdict format, the fix
loop, push gating, what leaves the machine, troubleshooting, and limits.
Linked from both READMEs, the Japanese quick reference, and the command docs.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-18 00:18:44 +09:00
kenima-arcandClaude Fable 5.1 946b80198f feat: add /astra-review cross-provider code review via Codex CLI
Send Claude-written code to GPT-6-Astra (Codex CLI, ChatGPT login) for an
independent review and return a structured PASS/FAIL verdict with
severity-tagged findings.

- commands/astra-review.md (+ ja-JP): review, fix, re-run workflow
- scripts/astra-review.js + scripts/lib/astra-review/{scope,prompt,codex}.js
- scopes: uncommitted, --base, --commit, --files, --files-from-commit
- reviewer isolation: read-only sandbox, web search off, user config
  skipped, every configured MCP server disabled by name, filtered env
- safe collection: no symlink following, repo containment, --no-ext-diff,
  NUL-delimited inventories, explicit failure on overflow
- 87 tests; registry, agent.yaml, package files, install manifest updated

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-18 00:07:00 +09:00
Affaan MustafaandClaude Fable 5.1 f8640355e4 Consolidate recovered eval framework and operator workflows (#3040)
* feat: consolidate offline eval and operator workflows

Compose the retained framework, operator skill, roadmap and cleanup ranges on current main. Preserve current release dependencies and keep candidate execution disabled pending OS containment. Repair draft/DOCX behavior, obligation uniqueness, trusted send and audience guidance, runner provenance and eval diagnostics.

Source-PR: 2930 0abe3727d2b500c6e4830bdeb47ed67cae3f4785
Source-PR: 2931 992b49c44ed872def49675b791168b8fcd091df6
Source-PR: 2932 4a193dd13041cb7a6bebf4d2e910a0cd32bcc797
Source-PR: 2933 59cdfe500a91949ba1415f1edd7279620f21e804
Source-Base: ca185ef5f7

* fix: repair foundation CI and update js-yaml

* fix: reconcile pending-delete capsule locks after close

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-10 13:20:52 +01:00
Wu Shuwen cc91c24f9a fix(commands): distinguish prp-pr alias (#2907) 2026-09-09 15:00:49 -04:00
iyashjayesh 51fe0e9163 Move token-card to a skill, pin the CLI, and fix three doc contradictions
Addresses the review on #3039. Four findings, all of them real.

Skills-first (Greptile P2). AGENTS.md says commands/ exists for compatibility and
the direction is skills-first, so the workflow now lives in skills/token-card
and commands/token-card.md is a thin shim pointing at it — 70 lines down to 28.

Unpinned remote code (CodeRabbit major, Greptile P1, CWE-494). The workflow ran
`npx -y @tokenchit/cli@latest` and handed whatever the registry currently serves
read access to local session logs. It is pinned to 0.7.0, the skill says to raise
the pin knowingly, gives the `npm view … dist.integrity` check, and step 1 is now
an explicit confirmation before the first download on a machine.

The "no network request" claim was false as written (both bots). `sync` sends
nothing, but the npx invocation around it is a registry download, and the
sentence read as though the whole step were offline. It now separates the two.

`--dry-run` wrote a file (Greptile P2). Step 1 created `.tokenchit.json` via
`init` before `sync --dry-run` ran, so a documented no-op mutated the tree.
Initialisation is skipped on a dry run and reported as prospective instead.

The README offer was unreachable (Greptile P2). "Stop after step 3" sat directly
below step 4, so the step that puts the card in the README — the whole point —
could never run. The boundary moved to after step 4; publishing still requires
being asked for by name.

Wiring: agent.yaml skills list, manifests/install-modules.json under
operator-workflows (beside cost-tracking and ecc-tools-cost-audit), and
package.json `files`, which the npm-publish-surface test requires to track the
module graph. `yarn install --mode=update-lockfile` leaves yarn.lock byte
identical, so nothing to commit there. docs/tr/AGENTS.md carries two skill counts
the catalog sync does not reach, both 286 -> 287.

npm test: 4396 passed, 0 failed. markdownlint clean on both files.
2026-09-09 12:58:07 +05:30
iyashjayesh 1052523127 feat(commands): add token-card command 2026-09-09 11:50:14 +05:30
Chisa Kotegawa 14c012966b fix(commands): avoid false security-scan skill relationship 2026-09-05 17:59:58 +08:00
Chisa Kotegawa a839c07939 fix(commands): clarify overlapping command triggers 2026-09-05 17:33:06 +08:00
haelyra 2aebdd3408 Merge pull request #2870 from actus7/consolidate/hooks-observer-v3
fix(hooks): consolidate hooks and observer fixes (5 PRs)
2026-08-28 18:29:03 -04:00
haelyra 96c4dc4a74 Merge pull request #2871 from actus7/consolidate/docs-v3
docs: consolidate documentation improvements (3 PRs)
2026-08-28 17:50:16 -04:00
Bechor Simhaev ea2ec0d249 fix(commands): use allowed-tools, not allowed_tools
Nine command files spell the key with an underscore while six other files in
this repository already use `allowed-tools`. Claude Code reads the hyphenated
form, so the underscored key is unrecognized and the tool pre-approval it is
meant to grant never applies.
2026-08-24 22:27:40 -03:00
Phumchai Tanonsi 774d64f51b docs: clarify model-generation reference in learn-eval rationale
The design rationale cited "Opus 4.6+" as the class of models capable of
holistic checklist judgment. That reference predates the Claude 5 families
(Opus 5, Sonnet 5, Fable 5), so readers on current models can't tell whether
the guidance still applies to them.

Widens the parenthetical to name the Claude 5 families explicitly. Applied
across all four locale copies (en, ja-JP, tr, zh-CN) to keep translations in
sync. Documentation wording only; no behavioral change.
2026-08-24 22:26:32 -03:00
Matt Van Horn 40c8235d48 fix: address self-review findings 2026-08-24 22:26:22 -03:00
haelyra d73009bbd1 fix(commands): route Santa reviewer through Antigravity wrapper 2026-08-11 13:39:42 -04:00
haelyra 3c8c20c506 Merge remote-tracking branch 'origin/main' into HEAD 2026-08-11 13:37:35 -04:00
Vitalii 74ffba6d4f fix: switch multi-model frontend routing from Gemini CLI to Antigravity CLI (#2520)
Google is sunsetting consumer Gemini CLI access on 2026-06-18 and
consolidating into Antigravity CLI. codeagent-wrapper already ships a
working AntigravityBackend (confirmed by shelling to `agy`), and
~/.claude/.ccg/prompts/antigravity/*.md role prompts already exist —
only the command markdown files still hardcoded --backend gemini.

Updates multi-frontend.md, multi-execute.md, multi-plan.md, and
multi-workflow.md to route frontend calls through --backend antigravity
instead of --backend gemini, point role-prompt paths at
prompts/antigravity/ instead of prompts/gemini/, and drop the
gemini-only --gemini-model flag (antigravity has no CLI equivalent;
codeagent-wrapper picks its default model).

multi-backend.md is unaffected (codex-only, no frontend routing).
2026-08-11 13:23:47 -04:00
Karim Farahat 203aac7710 fix(commands): probe for auto-update.js in auto-update ECC_ROOT resolver (#2462)
The auto-update command's inline ECC_ROOT resolver delegates to
resolveEccRoot() with the default probe (scripts/lib/utils.js). A
hooks-runtime-only install copies scripts/lib/ into ~/.claude, so the
partial install satisfies the probe and shadows the full plugin root
under ~/.claude/plugins/marketplaces/. The command then fails with
MODULE_NOT_FOUND because ~/.claude/scripts/auto-update.js does not
exist.

Pass {probe: scripts/auto-update.js} so the resolver only accepts a
root that actually contains the script the command runs. Applied to
the command doc and its ja-JP/zh-CN translations, with regression
tests for both the resolver behavior and the embedded snippets.
2026-08-04 00:28:59 -04:00
haelyra 85c7822c4a fix(commands): generate discoverable skills from learning workflows (#2653)
Carry #2246 forward on current main with native SKILL.md discovery, guarded writes, portable metadata, and fail-closed validation.
2026-08-02 14:39:29 -04:00
Leone Martins 3fed6f3cfe feat(commands): add Antigravity CLI (agy) as santa-loop Reviewer B option
Santa-loop's Reviewer B only tried codex and gemini before falling back
to a same-family Claude reviewer, losing model diversity when neither
was installed. Detect agy (Antigravity CLI, ~/.local/bin/agy) as a
third option, using gemini-3.6-flash-high — despite the "flash" name,
it currently outranks gemini-3.1-pro-high on every published
coding/agentic benchmark (SWE-Bench Pro, Terminal-Bench, MLE-Bench),
with Pro only ahead on PhD-level reasoning benchmarks that don't apply
to code review. Also documents never pointing agy at a Claude model,
which would collapse Reviewer A/B model diversity entirely.
2026-07-31 20:53:56 -03:00