Commit graph

14 commits

Author SHA1 Message Date
Claude
f11fccbb2b
fix(security): audit every changed skill and clear the 36 that failed
The skill security audit's detect step only looked for SKILL.md one or two
folders deep, so plugin-layout skills and engineering/skills mirrors were
skipped, and its path filter missed eleven newer domains. Detection now
walks up to the nearest SKILL.md, the path filter is gone, and the audit
re-runs on ready_for_review.

Before turning it on, all 409 skills pass `--strict`:
- Fixed: full-page-screenshot pasted the output path into shell commands
  and a generated Python script (execFileSync + JSON-quoted paths now);
  senior-fullstack scaffolds fell back to hardcoded secrets when the env
  var was unset (now required), and the scaffolder crashed on every
  template (str / str).
- Cleaned: senior-security's __import__('datetime'), epic-design's
  "You are now" opener.
- False positives marked with `noqa: SEC-AUDITOR (reason)`; the auditor
  gains an auditor:ignore-start/end block for template-string text.

Bumps every changed plugin one patch above dev (G11).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L8KYFLjaj5gnwaZdF3RyDn
2026-10-31 11:25:05 +00:00
Alireza Rezvani
a0c7b8f022
docs: replace command namespaces that no plugin provides (#1077)
Claude Code namespaces plugin commands by plugin.json name, so shorthand
prefixes never resolved: agenthub /hub: (now bare /hub-* and
/agenthub:spawn|eval|merge|board), executive-mentor /em: (now
/executive-mentor:<name>), docker/terraform/helm sub-commands (skill
arguments: /docker-development optimize), persona /pm: /devops:
/finance: /content: (now named workflows) and invented commands in the
Codex, Cursor and OpenClaw guides. check_command_refs.py now fails on any
/<prefix>:<name> whose prefix is not a plugin name. Drop redundant
'Use for /<cmd>, or' description leads (G12 shrinks 153 chars). Reserve
more CC 2.1.314 built-ins in check_skill_names.py. Bump changed plugins.


Claude-Session: https://claude.ai/code/session_01L8KYFLDu2gf1Jru9svgJHW

Co-authored-by: Claude <noreply@anthropic.com>
2026-10-31 07:47:03 +01:00
Claude
f511ceee7d
chore(release): bump changed plugins, refresh counters, G12 baseline, changelog
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L8KYFLGyaha8ReWA1JaCfC
2026-10-30 17:30:41 +00:00
Claude
91a20bafbd
fix(skills): link orphaned references and fix cross-plugin links
47 skills shipped reference files or CLI scripts that SKILL.md never
named, so the agent could not find them. Each now gets a short
'More in this skill' list with the file's own title.

Seven links pointed outside their plugin, which breaks once the plugin
is installed from the marketplace. c-level-agents now reaches
executive-mentor through a vendor/ symlink; the rest name the sibling
plugin instead of linking into it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L8KYFLGyaha8ReWA1JaCfC
2026-10-30 17:25:30 +00:00
Claude
b078bb8996
fix(skills): rewrite descriptions so skills trigger and fit the listing budget
Rewrites 347 SKILL.md descriptions across all 20 domains to a
when-to-load pattern: start with 'Use for/when/before', name the
moment the skill should load, and name the scripts it runs. Keeps
descriptions that were already in that shape and recently evaluated,
and leaves vendored skills (skillopt-sleep, loop-library) untouched.

Measured effect: the full marketplace's skill listing drops from
227,301 to 97,362 characters (with the earlier command flag), and a
9-skill marketing sample went from 3/36 to 11/36 exact triggers.

Derived indexes (.codex/.gemini/.vibe/.hermes skills-index.json and
the agent-harness domain manifests) are updated in place, description
fields only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L8KYFLGyaha8ReWA1JaCfC
2026-10-30 17:23:53 +00:00
Alireza Rezvani
ebbf6b0872
fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048)
Some checks failed
Sync Codex Skills Symlinks / sync (push) Has been cancelled
* fix(plugins): bump all plugins to 2.14.1 and gate unbumped changes

Claude Code caches plugins by version. 70 of 104 plugins changed between
v2.12.0 and v2.14.0 without a bump, so claude plugin update reported
"already at the latest version" and existing installs never received the
v2.13/v2.14 fixes. Every plugin moves to 2.14.1 so stale caches refresh once.

check_plugin_versions.py (G11, blocking in ci-quality-gate) fails when a
plugin's payload, including symlinked vendor files, changes without a higher
version, and when marketplace.json and plugin.json disagree.
bump_plugin_versions.py sets both together.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(codex): stop installing all skills by default

With the full library (~380 skills) Codex drops every skill description from
its prompt budget, so it cannot pick skills. codex-install.sh now asks for
--category (comma-separated), --skill or an explicit --all, lists categories
when run without arguments, and warns when more than ~100 skills are
installed. The Windows installer and install docs follow.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(gemini): link whole skill folders and drop duplicate mirror entries

Each .gemini/skills entry held only a SKILL.md symlink, so the relative
scripts/ and references/ a skill points to were missing. Entries are now
directory symlinks (Gemini CLI 0.65 discovers them). Dual-published copies
with identical SKILL.md are listed once, commands and agents that share a
skill's name are skipped, fixtures under assets/ and vendor/ re-exports are
excluded, discovery is sorted so reruns are stable, and stale generated
entries are pruned. gemini skills list: 20 conflicts -> 1 (handoff, fixed
next). GEMINI.md documents folder trust and fixes a dead example path.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(handoff): rename the productivity skill to session-handoff

engineering/handoff and productivity/handoff both shipped a skill named
handoff. Claude Code namespaces them, but Codex, Gemini CLI, Vibe and Hermes
key skills by name and silently kept one. The productivity skill is now
session-handoff (handoff-productivity:session-handoff); its folder, plugin
manifest, hook script paths, command paths, mirrors, harness manifest and
docs page follow. /cs-handoff, /cs-handoff-setup and ~/.config/handoff are
unchanged; the plugin README carries a migration note.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(convert): include plugins whose SKILL.md is at the plugin root

convert.sh searched at -mindepth 4, which skipped boost-asio-pro, deepread,
hivemind, loop-library, minimalist, strict-api and swedish-mentor for every
converted tool (opencode, Cursor, Windsurf, Kilo, Augment, Aider,
Antigravity). It now searches from depth 2 and skips assets/ fixtures.
opencode conversion: 375 -> 382 skills.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(codex): keep skill-tester's sample fixture from loading as a skill

Codex scans installed skill folders recursively and picked up
skill-tester/assets/sample-skill/SKILL.md as 'sample-text-processor'.
The installer renames SKILL.md files under assets/ in the installed copy.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(plugins): address scripts via ${CLAUDE_PLUGIN_ROOT} in commands and agents

343 script invocations in 90 command/agent files across 36 plugins used
repo-relative or ../ paths. Plugin commands and agents run from the user's
project, so those paths only resolved inside a clone of this repo; in the
v2.14.0 evals the agent fell back to find / to locate scripts. Every one now
uses ${CLAUDE_PLUGIN_ROOT}/. Two cross-plugin calls (write-a-skill ->
karpathy-coder, c-level-agents cpo -> product-manager-toolkit) go through
vendor/ symlinks, per the repo's install-cache lesson.

check_paths.py (G1) now fails a plugin command or agent that invokes a
script without ${CLAUDE_PLUGIN_ROOT}; on the v2.14.0 tree it reports 279.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(month-end-close): treat opening-balance rows as balances and pair transpositions

On a bank and GL export that each begin with an 'Opening balance' row, the
matcher returned RECONCILED_WITH_ITEMS and told the user to book a 25,000.00
journal entry for the opening balance, and it reported a 7,980/7,890
transposition as two unrelated items. Opening rows are now balances: a
difference between them is reported as carried in from the prior period
(R5, blocks sign-off, never booked). Same-date digit transpositions pair into
one correcting entry. The GL file's 'memo' column is read as description.
The v2.14.0 eval fixture now proves 1,405.00 = 150 opening + 90
transposition + 1,200 outstanding check - 35 bank fee. Bundled copy synced.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(coding-agent-rollout): flag connection-URL passwords and production MCP servers

On a committed .claude/settings.json holding
env.DATABASE_URL=postgresql://admin:<password>@prod-db... and
enabledMcpjsonServers: ["postgres-prod"], the linter flagged neither: the
env check only matched token formats and KEY/TOKEN/SECRET names. S11 now
catches a password embedded in any connection URL (BLOCKER in shared files),
and new S13 warns when a shared file pre-approves an MCP server whose name
marks it as production. Bundled copy synced; --sample output unchanged.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* docs: changelog and lessons for the v2.14.0 audit fixes

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-10-22 09:50:05 +02:00
Claude
0f88555485
chore(versioning,docs): normalize stale versions to 2.9.0 + refresh counts
Version normalization (scope: only plugins/skills older than 2.7.0):
- Bumped 52 plugin.json + 21 SKILL.md `version` fields from pre-2.7.0
  values (1.0.0 / 2.0.x / 2.2.x / 2.3.x / 2.4.x / 2.5.x) to 2.9.0.
  Left 2.7.0+ packages untouched. Tool mirrors (.codex/.gemini/.vibe/
  .hermes) excluded. All manifests still pass check_plugin_json --all.

Doc count refresh (recomputed raw figures: 338 skills, 16 domains,
62 plugins, 533 Python tools, 676 references):
- marketplace.json: both descriptions + metadata.version -> 2.9.0.
- Root README: headline, badges (Skills 338, Agents 51+, Commands 87+),
  intro counts, convert section (338 skills / 9 tools), and the full
  domain table rebuilt to 16 domains summing to 338 (adds research-ops,
  business-operations, commercial, compliance-os; corrects product 17,
  marketing 46, c-level 66, ra-qm 18, finance 4, engineering 51/78).
- Fixed stale per-skill README `Version:` lines left inconsistent by the
  bump (andreessen, c-level-agents, product-team, senior-qa).
- Fixed stale domain README footers (product-team 17/17, c-level 66/66,
  project-management 9/9).
- CLAUDE.md scope line, structure tree, highlight, and footer synced to
  the raw figures.

https://claude.ai/code/session_01PUNmQVE4WYvcrzpq2anC3D
2026-05-27 05:22:59 +00:00
Claude
8fd3155868
fix(plugin-schema): align with live Claude Code spec — migrate to "./"-prefixed skills field
Resolves #712 and #714.

Claude Code's plugin spec (code.claude.com/docs/en/plugins-reference) requires
"All paths must be relative to the plugin root and start with ./". CC 2.1.144+
rejects the bare "skills" form with `Validation errors: skills: Invalid input`,
breaking plugin installs from this repo.

Changes:
- 47 plugin.json manifests migrated from "skills": "skills" → ["./skills"]
  (canonical post-CC 2.1.144 form, also accepts string "./skills")
- scripts/check_plugin_json.py rewritten to enforce the live spec:
  * Hard-fails on non-"./"-prefixed strings (except the legacy "skills" literal)
  * Hard-fails on empty strings/arrays and non-string array entries
  * Emits WARN (non-fatal) on the legacy "skills" literal as a safety net
    for copied templates — the WARN tolerance can be removed later
  * Tested against all four canonical forms + 3 garbage forms
- CLAUDE.md §5 rewritten to document the live spec, including the historical
  context of the v2.1.107 → v2.1.144 regression window that's now closed
- 15 stale broken symlinks under .gemini/skills/ removed (orphans from older
  reorgs that the sync script didn't prune because its cleanup is disabled)

Verification:
- scripts/check_plugin_json.py --all → 0 FAIL, 0 WARN, exit 0 (69 files OK)
- pytest tests/ → 2103 passed
- find . -type l ! -exec test -e {} \; → 0 broken symlinks
- Live spec forms tested: ["./"], ["./skills"], "./skills", ["./a","./b"] all pass
- Garbage forms rejected: bare "./", empty array, non-string entries, plain strings
2026-05-21 07:03:11 +00:00
Claude
663bc8afa2
fix(plugin.json): drop "./" prefix from skills field to clear /doctor warning (#686)
Claude Code 2.1.133+ rejects "skills": "./skills" with a "Path escapes
plugin directory" warning, even though ./skills resolves to a valid
subdirectory inside the plugin root. Per the upstream docs example, the
correct value is "skills" (no ./ prefix), which works across all CC
versions and other tools (Codex, Gemini CLI, etc.).

Applied to all 47 plugin.json files that used "./skills"; updated
CLAUDE.md ClawHub publishing constraints to document the new convention
and reference the issue.
2026-05-19 03:43:34 +00:00
Reza Rezvani
c4801730f5 fix(plugins): restructure 21 single-skill plugins into ./skills/<name>/ layout
Claude Code v2.1.126 rejects "skills": ["./"] (array form) at runtime
with the same "Path escapes plugin directory: ./" error as the bare
string form, despite the official plugins reference docs explicitly
showing ["./"] as a valid example. `claude plugin validate` accepts it,
so the bug is in the runtime loader, not the manifest validator.

The proven workaround (already used for self-improving-agent in #536)
is to follow the canonical layout:

  <plugin>/
  ├── .claude-plugin/plugin.json    skills: "./skills"
  └── skills/<plugin-name>/
      ├── SKILL.md
      ├── scripts/
      ├── references/
      └── ...

Applied to 21 single-skill plugins:
- engineering-team/a11y-audit, google-workspace-cli, snowflake-development
- engineering/behuman, code-tour, data-quality-auditor, demo-video,
  docker-development, helm-chart-builder, karpathy-coder, llm-cost-optimizer,
  llm-wiki, prompt-governance, statistical-analyst, terraform-patterns
- finance/business-investment-advisor
- marketing-skill/video-content-strategist
- product-team/agile-product-owner, apple-hig-expert, code-to-prd,
  research-summarizer

Moved with each SKILL.md: scripts/, references/, assets/, templates/,
expected_outputs/. Kept at plugin root (per Claude Code requirements):
agents/, commands/, hooks/, settings.json, README.md.

Bumped patch version on each restructured plugin so /plugin update
picks up the new layout.

Refs #539
2026-05-02 22:33:59 +02:00
Reza Rezvani
2717c8f933 fix(plugins): bump versions to force /plugin update to pick up #587 fix
PR #587 fixed `"skills": "./"` in 35 plugin.json files but did not bump
versions. Claude Code uses version as the cache key — same version string
means /plugin update is a no-op and users keep loading the cached
plugin.json with the broken path. The /plugin UI shows "1 error" on
every plugin from this marketplace because the installed cache is stale.

Per the official version-management docs:
> If you set `version` in `plugin.json`, you must bump it every time
> you want users to receive changes. Pushing new commits alone is not
> enough.

Bump every plugin.json by one patch using max(plugin_version,
marketplace_version) as the base so no version moves backward. Sync the
new versions back into .claude-plugin/marketplace.json.

After this lands, users run `/plugin marketplace update claude-code-skills`
followed by `/plugin update --all` to pull the fixed manifests.
2026-05-02 22:14:12 +02:00
Reza Rezvani
55e7e45512 fix(plugins): repair skills path in 35 plugin.json files (#539)
Claude Code v2.1.107+ rejects bare "skills": "./" with "Path escapes
plugin directory: ./". This blocks every plugin in the marketplace from
loading. Replace with the layout-appropriate form per the official
plugins reference:

- Single-skill plugin (SKILL.md at root):
    "skills": ["./"]                  array form (per docs example)
- Plugin with skills/ subdir:
    "skills": "./skills"              standard subdir layout
- Multi-skill domain plugin (skills are subfolders at root):
    "skills": ["./sub1", "./sub2"]    explicit list of skill dirs

The multi-skill case omits "./" from the array so the index SKILL.md
at the plugin root does not register as a skill — that would create
a redundant `marketing-skills:marketing-skills` namespace.

Verified by running `claude plugin validate` against all 35 manifests.

Closes #539
2026-05-02 21:55:58 +02:00
Alireza Rezvani
5adbfdce47
release: sync dev → main — a11y-audit, /seo-auditor, /plugin-audit, 28 plugins (#380)
* fix: add missing plugin.json files and restore trailing newlines

- Add plugin.json for review-fix-a11y skill
- Add plugin.json for free-llm-api skill
- Restore POSIX-compliant trailing newlines in JSON index files

* feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375)

Adds review-fix-a11y (WCAG 2.2 a11y audit + fix) and free-llm-api skills.

Includes:
- review-fix-a11y: WCAG 2.2 audit workflow, a11y_audit.py scanner, contrast_checker.py
- free-llm-api: ChatAnywhere, Groq, Cerebras, OpenRouter, llm-mux, One API setup
- secret_scanner.py upgrade with secrets-patterns-db integration (1,600+ patterns)

Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223-alt@users.noreply.github.com>

* chore: sync codex skills symlinks [automated]

* Revert "feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375)"

This reverts commit 49c9f2109f.

* chore: sync codex skills symlinks [automated]

* Revert "feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375)"

This reverts commit 49c9f2109f.

* feat(engineering-team): add a11y-audit skill — WCAG 2.2 accessibility audit & fix (#376)

Built from scratch (replaces reverted PR #375 contribution).

Skill package:
- SKILL.md: 1132 lines, 3-phase workflow (scan → fix → verify),
  per-framework fix patterns (React, Next.js, Vue, Angular, Svelte, HTML),
  CI/CD integration guide, 20+ issue type coverage
- scripts/a11y_scanner.py: static scanner detecting 20+ violation types
  across HTML/JSX/TSX/Vue/Svelte/CSS — severity-ranked, CI-friendly exit codes
- scripts/contrast_checker.py: WCAG contrast calculator with AA/AAA checks,
  --suggest mode, --batch CSS scanning, named color support
- references/wcag-quick-ref.md: WCAG 2.2 Level A/AA criteria table
- references/aria-patterns.md: ARIA roles, live regions, keyboard interaction
- references/framework-a11y-patterns.md: React, Vue, Angular, Svelte fix patterns
- assets/sample-component.tsx: sample file with intentional violations
- expected_outputs/: scan report, contrast output, JSON output samples
- /a11y-audit slash command, settings.json, plugin.json, README.md

Validation: 97.6/100 (EXCELLENT), quality 73.9/100 (B-), scripts 2/2 PASS

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

* chore: sync codex skills symlinks [automated]

* docs: sync counts across all docs — 205 skills, 268 tools, 19 commands, 22 plugins

Update CLAUDE.md, README.md, docs/index.md, docs/getting-started.md,
mkdocs.yml, marketplace.json with consistent counts. Sync Gemini CLI
index with new skills (code-to-prd, plugin-audit).

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

* feat(marketplace): add 6 missing standalone plugins — total 22→28

Added to marketplace:
- a11y-audit (WCAG 2.2 accessibility audit)
- executive-mentor (adversarial thinking partner)
- docker-development (Dockerfile, compose, multi-stage)
- helm-chart-builder (Helm chart scaffolding)
- terraform-patterns (IaC module design)
- research-summarizer (structured research synthesis)

Also fixed version 1.0.0 → 2.1.2 on 4 plugin.json files
(executive-mentor, docker-development, helm-chart-builder, research-summarizer)

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

* feat(commands): add /seo-auditor — 7-phase SEO audit pipeline for documentation

- 7 phases: discovery → meta tags → content quality → keywords → links → sitemap → report
- Integrates 8 marketing-skill scripts: seo_checker, content_scorer,
  humanizer_scorer, headline_scorer, seo_optimizer, sitemap_analyzer,
  schema_validator, topic_cluster_mapper
- References 6 SEO knowledge bases for audit framework, AI search,
  content optimization, URL design, internal linking, AI detection
- Auto-fixes: generic titles, missing descriptions, broken links, orphan pages
- Preserves high-ranking pages — only fixes critical issues on those
- Registered in both commands/ (distributable) and .claude/commands/ (local)

Also: sync all doc counts — 28 plugins, 26 eng-core skills, 21 commands

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

* fix(seo): fix multi-line YAML description parser, add 2 orphan pages to nav

- generate-docs.py: extract_description_from_frontmatter() now handles
  multi-line YAML block scalars (|, >, indented continuation) — fixes
  14 pages that had 56-65 char truncated descriptions
- mkdocs.yml: add epic-design and research-summarizer to nav (orphan pages)
- Regenerated 251 pages, rebuilt sitemap (278 URLs)
- SEO audit: 0 broken links, 17→3 short descriptions, 278/278 pages
  have "Claude Code Skills" in <title>

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

---------

Co-authored-by: Leo <leo@openclaw.ai>
Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223@gmail.com>
Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223-alt@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 13:03:48 +01:00
Leo
bf1473b1be feat(skills): add research-summarizer and docker-development agent skills
research-summarizer (product-team/):
- Structured research summarization for papers, articles, reports
- Slash commands: /research:summarize, /research:compare, /research:cite
- Python tools: extract_citations.py (5 citation formats), format_summary.py (6 templates)
- References: summary-templates.md, citation-formats.md

docker-development (engineering/):
- Dockerfile optimization, compose orchestration, container security
- Slash commands: /docker:optimize, /docker:compose, /docker:security
- Python tools: dockerfile_analyzer.py (15 rules), compose_validator.py (best practices)
- References: dockerfile-best-practices.md, compose-patterns.md

Both skills include .claude-plugin/plugin.json and follow POWERFUL tier conventions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 22:47:16 +01:00