claude-skills/engineering/coding-agent-rollout
Alireza Rezvani ebbf6b0872
Some checks failed
Sync Codex Skills Symlinks / sync (push) Has been cancelled
fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048)
* 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-plugin fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
agents refactor(engineering): rename claude-code-team-rollout to coding-agent-rollout 2026-10-21 10:43:53 +00:00
commands fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
skills/coding-agent-rollout fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
README.md refactor(engineering): rename claude-code-team-rollout to coding-agent-rollout 2026-10-21 10:43:53 +00:00

coding-agent-rollout

One engineer's Claude Code setup is a preference. A team's is a policy.

Settings merge from five scopes, permissions.allow arrays combine across files, and deny beats ask beats allow wherever it is written. Nobody can read the effective policy from one file, so nobody notices when a permissive user file undoes a careful shared one, or when an unpinned MCP server changes overnight. This plugin makes the policy readable and then checks it.

Install

/plugin marketplace add alirezarezvani/claude-skills
/plugin install coding-agent-rollout

Use

/cs-claude-rollout .                         # full audit of this repo
/cs-claude-settings-lint . /etc/claude-code/managed-settings.json

Or run the scripts directly. Each has --help, --sample and --output json:

Script Phase What it checks Exit codes
settings_linter.py Guardrails Blanket and destructive allows, dead rules, secrets in env, committed local settings, MCP auto-approval, network hooks, managed bypass switch 0 · 2 · 3 · 4
mcp_plugin_inventory.py Inventory Every MCP server, plugin and marketplace; allowlist, pinning, plain-http remotes, committed secrets 0 · 2 · 3 · 4
claude_md_layering_audit.py Instructions Resident vs on-demand layers, @imports (4-hop limit), duplicates, contradictions, secrets, size 0 · 2 · 3 · 4
adoption_tracker.py Adoption Counts-only member summaries from local transcripts; team stage PILOT / SPREADING / EMBEDDED / STALLED 0 · 2 stalled · 3

Design decisions

  • Verified, not remembered. Every settings key, scope, path and limit was checked against the official Claude Code docs. Settings ship fast, so unknown keys are INFO, not errors.
  • Read-only. No script edits a settings file. They report; you decide.
  • Privacy first for adoption. The tracker never emits prompt text, file content, or tool inputs other than a skill name. Teams share the JSON summary, never transcripts.
  • Baseline policy included. assets/managed-settings.example.json lints clean and is a sane day-one policy.

Distinct from

  • claude-coach — coaches one person.
  • skill-doctor — improves installed skills from session evidence.
  • security-guidance — a hook that warns on risky code as it is written.

License

MIT