everything-claude-code

fix(agents): add Bash tool guardrails to agent-evaluator

List allowed read-only commands (grep, cat, ls, find, head, tail, wc, stat,
git log/diff/show) and explicitly forbid destructive commands (rm, mv, chmod,
git push, git commit, sudo, pip/npm install, curl|wget piping to sh). Any
write/delete/remote-push requires explicit user confirmation.

Hawthorn · 2026-06-10 18:18:58 +05:30

08f66b4909

fix: address second-round review comments

- Replace httpx.Retry references with correct httpx API usage across all files
  (httpx has no built-in Retry class; use HTTPTransport/Limits instead)
- Fix _check_summary to check first 100 words (not 100 characters)
- Fix template to only show → improvement arrow for non-5 scores
- Clarify hook documentation: hook echoes reminder, does not run evaluator
- Add return type annotation to main()
- Make required parameter keyword-only in _read_file_or_text

Hawthorn · 2026-06-10 17:59:25 +05:30

7c0a0049a8

fix: address self-evaluation review comments

- Clarify that agent-evaluator reads skills/agent-self-evaluation/SKILL.md directly
- Standardize on Conciseness terminology, including helper names
- Remove invalid Stop hook matcher and avoid unsupported command-expression matcher examples
- Add explicit hook-integration reference path in SKILL.md
- Add summary and self-check fields to evaluate.py output, template, and agent spec
- Refactor evaluate.py clarity and input parsing helpers
- Remove unused task parameter from check_completeness

Validation:
- python3 -m py_compile skills/agent-self-evaluation/scripts/evaluate.py
- evaluate.py high/low example smoke tests
- node scripts/ci/validate-agents.js
- node scripts/ci/validate-skills.js
- node scripts/ci/validate-hooks.js
- node scripts/ci/validate-no-personal-paths.js

Hawthorn · 2026-06-10 17:25:24 +05:30

2ea4d779a3

fix: align report format across evaluate.py, agent spec, and template

- evaluate.py: add CRITICAL ISSUES (axes ≤ 2) section, VERDICT line
- agent-evaluator.md: match format_report output exactly (title, evidence markers, bar graphs)
- templates/evaluation-report.md: match evaluate.py output format
- All now produce identical AGENT SELF-EVALUATION REPORT structure

Single authoritative format: evaluate.py's format_report() output.

Hawthorn · 2026-06-10 17:11:44 +05:30

c0f651cf85

Update agents/agent-evaluator.md

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

Hawthorn · 2026-06-10 17:08:31 +05:30

d0a84db177

feat(skills,agents): add agent-self-evaluation skill and agent-evaluator persona

Add structured 5-axis self-evaluation framework for agent output quality:
- Accuracy, Completeness, Clarity, Actionability, Conciseness
- Evidence-based scoring with concrete improvement suggestions
- Standalone Python evaluator script with keyword heuristics
- Detailed scoring anchors reference guide
- High-score and low-score annotated examples
- Reusable evaluation report template
- Optional hook integration for session-stop evaluation

Agent persona (agent-evaluator) provides a dedicated subagent
for applying the rubric to agent output with tool-backed verification.

All files tested: Python script runs, examples score correctly
(high 4.2, low 3.4), frontmatter parses clean, 183 lines (under 500).

Hawthorn · 2026-06-10 16:56:18 +05:30

bd45947941

docs: update Greptile sponsor placement

ECC Test · 2026-06-09 23:53:13 -04:00

c888d2b73f

feat(mcp): single-connector default set + connector policy (#2219 )

Reduce the default .mcp.json to one connector (chrome-devtools) per the
new policy in docs/MCP-CONNECTOR-POLICY.md: a default earns its slot only
if it is universal AND MCP beats a CLI/API wrapped in a skill. June 2026
audit verdicts: github -> gh via github-ops skill; context7 -> REST via
documentation-lookup; exa -> harness-native search (+ exa-search skill);
memory -> native harness memory + instincts; playwright -> playwright CLI
skills (vendor moved agent flows off MCP); sequential-thinking -> native
extended thinking. All six remain opt-in in mcp-configs/mcp-servers.json.
Tests updated: plugin-manifest policy assertions + install-apply Cursor
expectations.

Co-authored-by: ECC Test <ecc@example.test>

Affaan Mustafa · 2026-06-09 23:28:35 -04:00

ff768db363

ci: remove copilot code-review surface

ECC Test · 2026-06-09 21:42:38 -04:00

v2.0.0 8ad4151095

release: 2.0.0 — the agent harness operating system

Graduate 2.0.0-rc.1 to stable. Bump version across package, plugin,
marketplace, OpenCode, agent metadata, VERSION, and all localized docs.
Add 2.0.0 release notes + README sections (en/zh/pt-BR/tr), CHANGELOG
entry, and the ECC community Discord bot (dependency-free gateway client
+ guild command registrar). Update copilot-support and release-surface
tests for the sponsored-review migration and the 2.0.0 surface.

ECC Test · 2026-06-09 21:40:40 -04:00

29edd57708

ci: harden workflows and sponsor code review config

ECC Test · 2026-06-09 21:20:17 -04:00

3e30f1a56a

ci: harden release announce checkout

ECC Test · 2026-06-09 21:03:22 -04:00

10c303e609

docs: fix README markdownlint spacing

ECC Test · 2026-06-09 20:47:15 -04:00

4f69955f88

security: harden advisory intake and dependency coverage

ECC Test · 2026-06-09 20:46:14 -04:00

3c5bcc2b66

docs: refresh sponsor and readme surface

ECC Test · 2026-06-09 20:26:31 -04:00

8ee5946712

feat(discord): release -> #announcements auto-post + pin + GitHub Discussions (#2201 )

On a published GitHub release, post the notes to the ECC Discord
#announcements channel (via bot), pin it, and cross-post to GitHub
Discussions (Announcements category). Release data flows through env vars
(no shell interpolation of untrusted input). Secrets: DISCORD_BOT_TOKEN,
DISCORD_ANNOUNCE_CHANNEL_ID (repo secrets), GITHUB_TOKEN.

Ties the 2.0.0/1.11.0 official release to the community launch.

Co-authored-by: ECC Test <ecc@example.test>

Affaan Mustafa · 2026-06-08 22:38:03 -04:00

edebcc89ef

feat: add orch-* orchestrator skill family (#2153 )

* feat: add orch-* orchestrator skill family

Lightweight wrappers that orchestrate existing ECC agents through a gated Research -> Plan -> TDD -> Review -> Commit pipeline, right-sized per task.

- orch-pipeline: shared engine (phases, size classifier, two gates, agent map)
- orch-add-feature/change-feature/fix-defect/refine-code/build-mvp: thin wrappers delegating to the engine

* chore: register orch-* family in catalog, command registry, and agent.yaml (post-rebase onto green main)

---------

Co-authored-by: ECC Test <ecc@example.test>

David W Miller · 2026-06-07 16:15:31 +08:00

90dfd9505d

fix: make plugin hooks run on Node 21+ and green the suite under modern Node (#2184 )

ROOT CAUSE: hooks load plugin-hook-bootstrap.js via
`node -e "...; process.argv.splice(1,0,s); require(s)"`. On Node 21+,
require.main is `undefined` under --eval, so the `if (require.main === module)`
guard was false and main() never ran — every plugin hook silently no-op'd
(e.g. the MCP-health PreToolUse hook stopped blocking). CI (Node 18/20) hid
this; it only surfaces on Node 21+. Fix: also run main() when require.main is
undefined (the eval-bootstrap case), while staying dormant on real imports.

Also clears pre-existing main debt the full local suite enforces:
- catalog:sync — README/docs agent+skill counts drifted after recent merges
- tests/ci/supply-chain-watch-workflow: update checkout SHA to the merged v6.0.3 (#2183)
- markdownlint + check-unicode-safety --write across docs/skills

Suite: 2683/2683 green under Node v25; lint + unicode clean.

Co-authored-by: ECC Test <ecc@example.test>

Affaan Mustafa · 2026-06-07 16:05:28 +08:00

e755c5f72b

fix(codex): update bundled defaults to GPT 5.5 (#2132 )

Andrew Barnes · 2026-06-07 13:37:46 +08:00

eef31ad39c

feat(skills): add laravel-security, laravel-tdd, and php-reviewer agent (#2122 )

* feat(skills): add laravel-security, laravel-tdd, and php-reviewer agent

* fix: resolve code review findings across laravel-security, laravel-tdd, and php-reviewer

- laravel-security: replace env() with config() in runtime code,
  replace wildcard trusted proxies with CIDR ranges, remove blanket
  api/* CSRF exclusion, fix validated() return type, add null-safe
  rate limiter user access, sync mimes/extensions allowlists,
  replace #[Encrypted] with ShouldBeEncrypted, fix RateLimited args
- laravel-tdd: remove global withoutExceptionHandling() from setUp,
  remove contradictory assertNothingOutgoing(), fix undefined
  variable, replace invalid PHPUnit --min-coverage flag
- php-reviewer: fix Python contamination, add automated check
  requirement to approval criteria

* fix: align php-reviewer approval criteria and use config dot-notation keys

- agents/php-reviewer.md: sync approval criteria with .txt file version
  (add automated checks requirement for consistency across harnesses)
- skills/laravel-security/SKILL.md: replace raw env names with proper
  Laravel dot-notation config keys (app.key, services.stripe.*, etc.)
  so config() returns valid values instead of null

* fix: remove unnecessary secret validation for SMTP password

elmochilyas · 2026-06-07 13:29:12 +08:00

06c376ae8b

feat(skills): add fastapi-patterns skill (#2129 )

V Karthikeyan Nair · 2026-06-07 13:29:10 +08:00

66e28b5fb1

docs: fix renamed-repo links, drop stale assessment artifacts (#2058 )

CONTRIBUTING.md still pointed at the old `affaan-m/everything-claude-code`
repo URL in the Quick Start fork instructions and in the Issues link at
the bottom. Both relied on GitHub's silent rename-redirect, but the
literal `cd everything-claude-code` after `gh repo fork` would land in
the wrong directory now that the repo is `affaan-m/ECC`.

REPO-ASSESSMENT.md and EVALUATION.md were both 2026-03-21 personal
fork-audit artifacts written from one user's specific install. They
describe the project as a fork at `Infiniteyieldai/everything-claude-code`
v1.9.0 with 28 agents / 116 skills / 59 commands and pin the recommended
mode at "use as upstream tracker". None of that is true anymore (this
IS the upstream, v2.0.0-rc.1, currently 61 / 246 / 76). EVALUATION.md in
particular still references a defunct branch (`claude/evaluate-repo-comparison-ASZ9Y`)
and describes a "Current Setup" of zero installed components as if it
were universal, which it is not.

Neither file is referenced by anything else in the repo (`rg` confirmed)
and they actively mislead new contributors and visitors. Delete both.

A targeted line-by-line refresh of EVALUATION.md was considered but
rejected: bringing only the totals up to date (61/246/76) would leave
the rest of the document — v1.9.0 references, branch metadata, the
zero-component "Current Setup" — internally inconsistent (CodeRabbit
flagged this on the first revision of this PR). Wholesale removal is
the honest fix.

Translated copies (e.g. docs/pt-BR/README.md still has the 28/116/59
numbers) are intentionally left for a follow-up i18n PR to keep this
diff small.

fxdv · 2026-06-07 13:27:08 +08:00

d2dfca21a4

fix(commands): resolve active plugin root in /instinct-status (#2037 ) (#2059 )

The `/instinct-status` slash command template expanded
`${CLAUDE_PLUGIN_ROOT}` directly and documented a manual-install
fallback to `~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py`.
When users had both an active plugin install (under
`~/.claude/plugins/cache/<slug>/<org>/<version>/`) and a legacy
`~/.claude/skills/continuous-learning-v2/` directory left over from a
previous manual install, an empty `CLAUDE_PLUGIN_ROOT` (which Claude
Code does not always populate in slash-command shell contexts) silently
made the command read the stale legacy install while the active plugin
hooks and observer wrote to the new XDG path. The user saw "No
instincts found" while the system was actively learning — exactly the
divergence the bug reporter spent hours diagnosing.

Replace the brittle two-block template with the same inline resolver
pattern that `hooks/hooks.json` and `/sessions` / `/skill-health`
already use: env var → standard install → known plugin roots → plugin
cache walk → fallback. The resolver is the canonical `INLINE_RESOLVE`
constant from `scripts/lib/resolve-ecc-root.js`, so no new code is
introduced — just consistent adoption of the existing pattern.

Apply the same fix to all five copies of the command:
  - commands/instinct-status.md (canonical)
  - .opencode/commands/instinct-status.md
  - docs/zh-CN/commands/instinct-status.md
  - docs/ja-JP/commands/instinct-status.md
  - docs/tr/commands/instinct-status.md

Extend tests/lib/command-plugin-root.test.js with an assertion that the
canonical instinct-status.md uses the inline resolver and no longer
hard-codes the legacy `~/.claude/skills/...` fallback (regression
guard).

zh-CN copy: polish the Chinese phrasing per LanguageTool feedback
(`使用与 ... 相同的解析器` → `以与 ... 相同的解析器`) so the verb is
introduced by an explicit preposition instead of reading as an awkward
verb-object construction.

fxdv · 2026-06-07 13:27:05 +08:00

8eedcff5ac

docs: add Urdu (ur) README translation (#2061 )

* docs: add Urdu (ur) README translation

Adds docs/ur/README.md — a full Urdu translation of the main README.
Urdu is spoken by 230M+ people globally, with a large developer community
in Pakistan. This follows the same structure as existing translations
(de-DE, ja-JP, ko-KR, etc.).

* docs(ur): sync install catalog counts with current repo metadata

The Urdu README stated 60 agents / 232 skills / 75 legacy command shims, but the current repo metadata and English README use 61 / 246 / 76. Update to match so Urdu users following the install guide do not see a verification mismatch (flagged in review).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

zucchini · 2026-06-07 13:27:03 +08:00

d7dcd10c8a

feat: Cursor-independent ECC memory via ECC_AGENT_DATA_HOME (#2066 )

* feat: auto-isolate ECC memory data for Cursor via ECC_AGENT_DATA_HOME

Add ECC_AGENT_DATA_HOME (defaults to ~/.claude) with Cursor-aware resolution,
sessionStart env injection, install scaffolds, and hook bootstrap so memory
hooks do not collide with Claude Code when both harnesses are used.

Closes #2065

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix: log agent-data config errors and ship cursor sessionStart deps

Address CodeRabbit review: log invalid .cursor/ecc-agent-data.json parse
failures, and copy cursor-session-env.js plus lib deps on legacy Cursor
install so sessionStart hook path exists without hooks-runtime alone.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix: resolve relative agentDataHome paths from project root

Project config values like ".ecc-data" now resolve against the
repository root (parent of .cursor/), not process.cwd(), so Cursor
hooks persist memory in the intended directory regardless of hook cwd.

Addresses cubic review on PR #2066.

Co-authored-by: Cursor <cursoragent@cursor.com>

* docs: explain getHomeDir duplicate and docstring policy

Document why agent-data-home keeps a local home-dir helper (circular
require with utils.js) and list consolidation options for maintainers.
Note that CodeRabbit JSDoc coverage warnings are informational relative
to ECC's usual script documentation style.

Addresses cubic P2 context on PR #2066.

Co-authored-by: Cursor <cursoragent@cursor.com>

* test: isolate agent-data-home tests from dogfooded .cursor config

Use isolated temp cwd for default-resolution cases and assert
resolveAgentDataHome({ projectDir }) reads ecc-agent-data.json.
Document cwd/project caveats in the test file header.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

Tom Cruise Missile · 2026-06-07 13:27:00 +08:00

6a40469408

fix(docs): sync marketplace add URL across translated READMEs (#2050 ) (#2068 )

PR #2050 updated the root README.zh-CN.md install commands after the
everything-claude-code → ECC rename, but the same stale marketplace URL
remained in nine docs/<locale>/README.md copies. Align those quick-start
and self-hosted install blocks so /plugin install ecc@ecc resolves the
ecc marketplace instead of everything-claude-code.

Infinity_Block · 2026-06-07 13:26:58 +08:00

81c9150512

feat(skills): add codehealth-mcp skill and CodeScene MCP config (#2077 )

* feat(skills): add codehealth-mcp skill and CodeScene MCP config

* docs(skills): add When to Use, How It Works, and Examples sections

* docs(skills): clarify MCP opt-in, data boundaries, and offline behavior

Address security review on PR #2077: no bundled credentials, document what
tools read locally, failure behavior when MCP is unavailable, and README
wording that Code Health MCP is optional and not enabled by default.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: adnasalk-notus <adna.salkovic@notus.hr>
Co-authored-by: Cursor <cursoragent@cursor.com>

Adna Salković · 2026-06-07 13:26:54 +08:00

07812091aa

feat(mcp): add parallel-search server catalog entry (#2085 )

* feat(mcp): add parallel-search server catalog entry

* fix(mcp): drop placeholder Bearer header from parallel-search entry

The /mcp endpoint accepts anonymous requests by default; baking in a
placeholder "Authorization: Bearer YOUR_PARALLEL_API_KEY_HERE" header
breaks the key-free default for users who copy the entry verbatim.
Move the optional API-key guidance into the description instead.

Matt H · 2026-06-07 13:26:51 +08:00

154d0c7de9

fix(context-monitor): make cost warnings informational, not commands (#2091 )

The PostToolUse cost warnings emit imperative text via additionalContext
("Stop and inform the user...", "Review whether...", "Consider whether...").
Subagents read additionalContext as an instruction and obey the "Stop",
abandoning their task and returning a prompt-for-direction instead of their
result — derailing multi-agent workflows. The main loop is also nudged to
halt mid-task.

Reword all three severities to pure-informational data: keep the
CRITICAL/WARNING/NOTICE label + the dollar figure (and the threshold), drop
the imperative sentence, and state plainly it is informational. No logic,
severity, or threshold change. Existing tests pass (they assert the labels +
severities, which are preserved).

Before: `COST CRITICAL: Session cost is $X. Stop and inform the user about high cost before continuing.`
After:  `COST CRITICAL: session total ~$X (over $50). Informational only — not an instruction to stop.`

Co-authored-by: OrenG Tools <tools@orengacademy.com>

Farzul Nizam Zolkifli · 2026-06-07 13:26:48 +08:00

1e5fa96d75

feat: add intent-driven-development skill (#2092 )

* feat: add intent-driven-development skill

Converts ambiguous feature or engineering requests into scoped,
verifiable acceptance criteria before implementation starts.

- Chooses between Quick Capture (low/moderate risk) and Full
  Acceptance Brief (security, data, migration, cross-system changes)
- Reads repo context before asking questions; only asks what cannot
  be inferred
- Non-blocking by default: records criteria and proceeds unless a
  real risk requires confirmation
- Rule 9: when an AC fails mid-implementation due to architectural
  constraints, marks it [revised], updates scope/verification method,
  and re-presents only changed criteria rather than silently dropping
- Output template includes Revision Log for traceability across
  multiple implementation cycles

* fix: add canonical When to Activate, How It Works, and Examples sections

Required for auto-activation mechanism detection per CONTRIBUTING.md
and existing skill conventions. Sections inserted after the intro
and before Operating Rules.

* fix: strengthen intent-driven-development skill per review

Address skill-quality review feedback on the intent-driven-development PR:

- Business/product constraints: add Operating Rule 2 forbidding inference
  of business rules, compliance/SLAs, pricing, retention, prioritization,
  and target users from code; surface the technical-vs-business split in
  How It Works, Discover Context, and a dedicated 'supplied, not inferred'
  section in the brief template.
- Eval-style pass/fail: add a Pass/Fail Examples section (failing vs
  passing AC, plus a misplaced business-rule context entry) and a 5-point
  Pass/Fail Rubric users can apply to the output.
- Renumber Operating Rules 1-10 accordingly; markdownlint clean.

Andrea Cavallo · 2026-06-07 13:26:45 +08:00

ff1bfa1b77

docs: add Spanish (es) translation (#2095 )

Adds a complete Spanish translation of the ECC documentation under
docs/es/, mirroring the Turkish (docs/tr/) translation in scope.
141 files covering agents, commands, rules, skills, contexts, examples,
and core docs. Updates root README.md with the Spanish language link.

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

Santiago González Siordia · 2026-06-07 13:26:42 +08:00

ac0f11c640

feat: add inherit-legacy-style — prevent AI code style drift in legac… (#2098 )

* feat: add inherit-legacy-style — prevent AI code style drift in legacy projects

- 4-dimension meta-architecture scan (File Anatomy, State & Control Flow, Infrastructure, Error Handling)
- Scale-adaptive (small=full read, large=smart sampling)
- Signal-threshold noise reduction with one-at-a-time grilling protocol
- Generates .ai-style-rules.md with persistent CLAUDE.md hook
- Language- and framework-agnostic

* fix: add AskUserQuestion to allowed-tools, add When to Use/How It Works/Examples sections per bot review

---------

Co-authored-by: wulinzai <linsywu@gmail.com>

linsy · 2026-06-07 13:26:40 +08:00

28b78dd7bf

feat: expand Kiro adapter to full language coverage (#2101 )

* feat: expand Kiro adapter to full language coverage

- Add 17 new agents (typescript, rust, kotlin, java, cpp, django, swift,
  fsharp, pytorch, mle, performance-optimizer) in both .md and .json formats
- Add 25 new skills (rust, kotlin, java/spring, django, fastapi, nestjs,
  react, nextjs, cpp, swift, mle/pytorch, deep-research, strategic-compact,
  autonomous-loops, content-hash-cache-pattern)
- Add 6 new language-specific steering files (rust, kotlin, java, cpp, php, ruby)
- Add 3 new hooks (rust-check-on-edit, python-lint-on-edit, security-check-on-create)
- Update README with expanded component inventory and documentation
- Fix install.sh line endings for macOS compatibility

Total Kiro components: 33 agents, 43 skills, 22 steering files, 13 hooks

* fix: resolve P1/P2 violations in Kiro agents, skills, and steering

- java-patterns.md: remove reference to non-existent quarkus-patterns skill
- kotlin-patterns.md: fix insecure BuildConfig recommendation for secrets
- swift-actor-persistence: fix Swift version claim (5.9+) and Dictionary crash
- java-reviewer.md: add recursive framework detection + robust diff chain
- kotlin-reviewer.md: replace unreliable diff detection with fallback chain
- rust-reviewer.md: add diff fallback + make CI gating mandatory
- jpa-patterns: add DISTINCT to fetch-join query to prevent duplicates
- django-reviewer.md: add migration safety check, narrow save() rule,
  fix pytest-django behavior description

* fix: resolve remaining violations in Kiro agents, skills, and docs

Agents:
- java-build-resolver.md: remove quarkus-patterns ref, fix 'Initialise' spelling
- java-reviewer.json: remove quarkus-patterns ref from prompt
- mle-reviewer.md, cpp-build-resolver.md, java-build-resolver.md,
  performance-optimizer.md: fix allowedTools 'read' -> 'fs_read'

Hooks:
- rust-check-on-edit: fix description to match askAgent behavior

Skills:
- content-hash-cache-pattern: hyphenate 'Content-Hash-Based'
- cpp-testing: hyphenate 'real-time'
- django-security: use placeholder secrets, fix CSRF_COOKIE_HTTPONLY=False
- nestjs-patterns: add Logger to HttpExceptionFilter for non-Http errors
- react-patterns: add React 19 compatibility note for useActionState
- rust-patterns: remove edition-specific 'Rust 2024+' reference
- springboot-patterns: cap exponential backoff, recommend Resilience4j
- springboot-security: fix invalid @Query SQL injection example
- swift-protocol-di-testing: add thread-safety doc comment to mock

Docs:
- README.md: fix Project Structure counts (33/43/22/13)

* fix: sync README tree with counts, restore local diff in kotlin-reviewer, correct django FK index guidance

- README.md: Project Structure tree now lists all 33 agents, 43 skills,
  22 steering files, and 13 hooks (was showing old subset)
- kotlin-reviewer.md: restore git diff --staged / git diff for local
  pre-commit review before falling back to HEAD~1
- django-reviewer.md: clarify that ForeignKey fields are indexed by
  default; only flag missing db_index on non-FK filter columns

Vu Thanh Tai · 2026-06-07 13:26:37 +08:00

4ad5756899

docs: fix typos in security guide (#2106 )

Correct clear spelling mistakes in documentation without changing behavior.

Confidence: high
Scope-risk: narrow
Tested: git diff --check; uvx codespell on changed files
Not-tested: Full docs build not run; text-only changes

Zhao73 · 2026-06-07 13:26:34 +08:00

4b3a269bd9

feat(desktop-notify): route OSC 9 notifications through Ghostty (#2114 )

Ghostty natively supports the OSC 9 desktop-notification escape
(ESC ] 9 ; <message> BEL), the same sequence already used for iTerm2.
Previously only TERM_PROGRAM === 'iTerm.app' took the escape path, so
Ghostty users fell through to the osascript path. That makes Script
Editor the notification owner, and clicking the notification just
launches Script Editor instead of focusing the terminal.

Adding 'ghostty' to the OSC 9-capable check makes Ghostty the owner,
so clicking the notification focuses the Ghostty window/tab where
Claude Code is running. Verified on Ghostty (TERM_PROGRAM=ghostty).

Co-authored-by: 高野智史 <satoshitakano@takanosatoshinoMacBook-Pro-522.local>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

satoshi-takano-bloom · 2026-06-07 13:26:32 +08:00

80c63c88f0

fix(hooks): stop false loop warnings and repeated identical context warnings (#2121 )

* fix(hooks): stop false loop warnings and repeated identical context warnings

Two PostToolUse monitor defects surfaced during a long single-turn session:

1. ecc-metrics-bridge hashToolCall fingerprinted Edit/Write/MultiEdit on
   file_path ONLY, so several distinct edits to the same file produced the
   same hash and tripped the loop detector ("stuck loop") even though every
   edit was different. Now the hash includes the edit content
   (old_string/new_string/content/edits) so distinct edits to one file hash
   differently; identical edits still collide as intended.

2. ecc-context-monitor re-emitted the SAME warning every DEBOUNCE_CALLS (5)
   tool calls even when nothing changed. Because the cost figure only refreshes
   at Stop (turn) boundaries, a single stale value printed the identical
   warning ~20 times within one turn. Dedupe on message content instead: a
   warning surfaces only when its text changes (cost moved, new file count, new
   loop) or on first escalation to critical, and is otherwise suppressed.

Adds regression tests for the same-file/different-content hash case.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(hooks): address CodeRabbit review (#2121)

- ecc-context-monitor: clear dedupe state when warnings resolve, so the same
  warning text recurring in a later turn (context dips/recovers/dips, a loop
  that stops then restarts) is surfaced again instead of suppressed as a
  duplicate. Guarded so the no-warning hot path stays write-free.
- ecc-metrics-bridge: hash the FULL serialized edit payload and truncate the
  digest, not the input. Slicing the serialized string to HASH_INPUT_LIMIT
  first could collapse large edits sharing their first 2048 chars, reviving the
  false-loop collision for big Write/edit payloads.
- Add regression test for >2048-char edit divergence.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

AHNINE Amine · 2026-06-07 13:26:30 +08:00

4197ea545f

Add NEXUS to mcp-configs/mcp-servers.json (local cost/privacy proxy) (#2125 )

* Add NEXUS to mcp-configs/mcp-servers.json

NEXUS (github.com/lynuxis2026-pixel/nexus-proxy) is a local, single-binary
cost/privacy proxy that sits under the harness. Adding it as an MCP server lets
an ECC agent query its own usage/savings mid-session (nexus_stats, nexus_savings,
nexus_recent, nexus_providers, nexus_cost_breakdown).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* Tighten nexus MCP description to ECC's concise house style

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: ludicolijn1985-blip <ludicolijn1985@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

lynuxis2026-pixel · 2026-06-07 13:26:27 +08:00

5df520658a

fix(trae): strip trailing slash so skill manifest entries are single-slash (#2126 )

The Trae installer recorded nested skill files with a doubled slash
(e.g. `skills/skill-comply//pyproject.toml`). The skills loop used the
glob variable `$d`, which carries a trailing slash, both as the `find`
root and as the prefix removed from each file path. Under bash, BSD
`find` with a trailing-slash argument emits `.../skill-comply//file`, so
`${source_file#$d}` left a leading slash, producing double-slash manifest
entries that did not match the single-slash paths uninstall.sh expects.

Strip the trailing slash from `$d` and remove the `$d/` prefix so `find`
emits clean paths and manifest entries are single-slash. Fixes the
previously failing test in tests/scripts/trae-install.test.js
("records nested skill files and the full rules tree in the manifest").

Co-authored-by: affaan-m <tamiraw808@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

0xJayHK · 2026-06-07 13:26:25 +08:00

54578415cd

fix: surface legacy data warning in instinct-cli status (#2127 )

* fix: surface legacy data warning in instinct-cli status (#2036)

When the data directory moved from ~/.claude/homunculus/ to the
XDG-compliant ~/.local/share/ecc-homunculus/, legacy installs with data
still in the old path saw "No instincts found" with no explanation.

Add _warn_legacy_data() to cmd_status so users get a clear, actionable
warning pointing them to the migration script or the CLV2_HOMUNCULUS_DIR
override. Wrap the directory scan in try/except to handle permission
errors gracefully.

Closes #2036

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix: address review feedback — drop unused f-strings, resolve absolute migrate path

Remove extraneous f-prefix from strings without interpolation (ruff F541).
Resolve migrate-homunculus.sh path relative to instinct-cli.py instead of
hard-coding a repo-relative path that only works from the repo root.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix: quote migrate script path to handle spaces

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: kky <lingmu141592@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

xiaoxi · 2026-06-07 13:26:22 +08:00

e4dfc1679b

docs: quote pip extras install example (#2130 )

Co-authored-by: nyxst4ck <289980115+nyxst4ck@users.noreply.github.com>

nyxst4ck · 2026-06-07 13:26:20 +08:00

3248ac69f0

fix: normalize POSIX CLAUDE_PLUGIN_ROOT to Windows path in hook bootstrap (#2139 )

Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>

Matt Van Horn · 2026-06-07 13:26:17 +08:00

9adaa88999

fix: shrink default OpenCode install surface and gate hooks-runtime (#2140 )

Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>

Matt Van Horn · 2026-06-07 13:26:14 +08:00

80233f1b72

Fix claude-project target for legacy language installs (#2147 )

Adilan Akhramovich · 2026-06-07 13:26:11 +08:00

53d4b7d664

fix(gateguard): gate force/path git checkout as destructive (#2158 )

* fix(gateguard): gate force/path git checkout as destructive

The destructive-command gate's `checkout` handler only flagged
`git checkout -- <path>`. It missed `git checkout --force` / `-f <branch>`
and `git checkout .`, all of which discard uncommitted working-tree changes,
so they bypassed the gate (once the once-per-session routine-Bash gate is
satisfied, they ran with no challenge). The sibling `switch` handler already
covers these force forms; mirror it for `checkout`.

* test(gateguard): document Test 7b force-checkout case

---------

Co-authored-by: bymle <229636660+bymle@users.noreply.github.com>

bymle · 2026-06-07 13:26:08 +08:00

0cb8907e14

docs(claude): install manual skills at top level (#2160 )

* docs(claude): install manual skills at top level

* test(docs): guard Claude manual skill install path

* test(docs): detect PowerShell/$HOME nested skill-install paths

Address CodeRabbit on #2160: the nested-path regression guard only matched
Unix `mkdir`/`cp` with `~`, so a reintroduced PowerShell `Copy-Item ...
$HOME/.claude/skills/ecc` (or backslash-separated) form would have slipped
through. Extend the pattern to also cover `Copy-Item`/`New-Item` (and the
`md`/`copy`/`cpi` aliases), accept `$HOME` as an alternative to `~`, allow both
`/` and `\` separators, and match case-insensitively.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

Kumario · 2026-06-07 13:26:06 +08:00

680cc7153b

fix: truncate corrupted legacy command shims (#2167 )

tdd.md, e2e.md, and orchestrate.md in legacy-command-shims/commands/ still
carried their full pre-shim command bodies concatenated below the shim
headers: a stray '})' and orphaned code fence in tdd.md, leftover Playwright
test bodies plus a foreign project-specific 'PMX-Specific Critical Flows'
section in e2e.md, and orphaned report-template fragments in orchestrate.md.
The trailing bodies also contradicted the shim headers by claiming the
commands invoke agents directly.

Truncate each file at the end of its Delegation section. The other nine
legacy shims are clean 20-23 line shims and are untouched.

konstapukarifastnetfi · 2026-06-07 13:26:03 +08:00

be536c1a3e

fix: refresh stale technical content in agents, rules, and skills (#2168 )

Several published examples contained APIs that no longer exist, code that
does not run, or model versions that drifted from reality:

- agents/performance-optimizer.md used the web-vitals v3 API
  (getCLS/getFID/getLCP/getFCP/getTTFB) and reported FID. web-vitals v4
  renamed the imports to onCLS/onINP/onLCP/onFCP/onTTFB and FID was
  replaced by INP (target < 200ms)
- rules/common/performance.md pinned stale model versions in the
  model-selection guidance; refresh to the versions the repo itself uses
  (agent.yaml pins claude-opus-4-6) and add the PowerShell variant for
  MAX_THINKING_TOKENS next to the bash export
- skills/python-patterns/SKILL.md: both get_value examples referenced
  default_value without declaring the parameter (NameError); add
  default_value: Any = None to the EAFP and LBYL signatures
- skills/frontend-patterns/SKILL.md: the custom useQuery example rebuilt
  refetch whenever callers passed inline fetchers/options, re-triggering
  the effect after every state update (infinite fetch loop). Keep the
  latest fetcher/options in refs so refetch stays referentially stable.
  The PASS-labelled useMemo example mutated its input with in-place sort;
  copy before sorting
- skills/coding-standards/SKILL.md repeated the same PASS-labelled
  in-place-sort-in-useMemo example; same fix
- rules/typescript/security.md used a vendor-specific OPENAI_API_KEY in
  generic guidance; switch to a neutral API_KEY

Every hand-maintained copy of the affected content is synced in the same
change: locale mirrors (ja-JP, ko-KR, pt-BR, tr, zh-CN, zh-TW - each only
where it carries the affected file) and the .agents/.kiro/.cursor harness
mirrors. Two structural divergences are left alone and noted here:
.kiro/steering/performance.md has no extended-thinking control list to
carry the PowerShell variant, and docs/zh-TW/rules/performance.md keeps an
older condensed thinking section without the budget-cap line.
rules/zh/performance.md is intentionally untouched - the rules/zh tree is
being retired in a separate change

konstapukarifastnetfi · 2026-06-07 13:26:01 +08:00

8b24f63ede

docs: align command docs with shipped behavior (#2169 )

- multi-{plan,execute,backend,frontend,workflow}.md: add an in-file
  prerequisite note for the external ccg-workflow runtime. README.md already
  warns these commands need codeagent-wrapper and the .ccg prompt tree, but
  users meeting them via the installed slash commands never see the README;
  the commands-core module still installs all five by default
- quality-gate.md: describe what scripts/hooks/quality-gate.js actually does.
  The doc advertised '/quality-gate [path] [--fix] [--strict]' with lint/type
  checks, but the script reads the file path from hook stdin JSON, toggles
  behavior via ECC_QUALITY_GATE_FIX / ECC_QUALITY_GATE_STRICT env vars, and
  runs formatters only (Biome/Prettier, gofmt, ruff format)
- claude-devfleet SKILL.md: add a Setup section pointing at the DevFleet
  server repository (github.com/LEC-AI/claude-devfleet, already disclosed in
  mcp-configs/mcp-servers.json) plus the SECURITY.md port-verification note;
  the skill previously assumed a running instance with no way to obtain one
- regenerate docs/COMMAND-REGISTRY.json for the quality-gate description

konstapukarifastnetfi · 2026-06-07 13:25:58 +08:00

36bec90d45

fix: retire rules/zh from the always-loaded default rules install (#2170 )

rules/zh shipped ~17KB of Chinese rule text into the auto-loaded rules tree
of every default install (rules-core installs the bare 'rules' path with
defaultInstall: true), with no paths: frontmatter gating. The content had
also drifted behind both rules/common and the maintained translations in
docs/zh-CN/rules/common (e.g. zh/coding-style.md 48 lines vs the 52-line
docs/zh-CN copy), and 'zh' was already dropped from the installer's language
help in favor of the gated docs-zh-cn locale module (--locale zh-CN).

- move rules/zh/code-review.md to docs/zh-CN/rules/common/code-review.md:
  the only file with no counterpart in the maintained locale tree (fills a
  zh-CN parity gap with rules/common/code-review.md)
- delete the remaining 10 rules/zh files, all older duplicates of
  docs/zh-CN/rules/common content
- update trae-install test to assert the rules tree via rules/web instead

Not addressed here: rules/README.md (~5.5KB of installer docs) still ships
into the auto-loaded tree via the bare 'rules' module path; filtering README
files from rule-tree expansion is a separate decision

konstapukarifastnetfi · 2026-06-07 13:25:56 +08:00

5dc60a5243

test: skip chmod-based permission tests when running as root (#2171 )

Two tests provoke EACCES via chmod (saveAliases backup double failure,
appendSessionContent on a read-only file) and already skip on win32, but
root ignores file modes so both fail when the suite runs as root (for
example in a default Docker container). Every other chmod-based test in
the repo already guards with process.getuid?.() === 0; these two were the
only ones missing the guard. Apply the same skip condition and message.

konstapukarifastnetfi · 2026-06-07 13:25:53 +08:00

6614f79fe3

2070 Commits