shared
Shared agent skills catalog, read in place from this repository.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin shared in cbusillo/codex-skills. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
What it installs
Skills (27)
babysit-prBabysit a GitHub pull request by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep
directionUse when the Director starts a direction session, asks for a north star, dead reckoning, a daily or weekly direction check, a direction audit, or milestone proposals; when a repository's DIRECTION.md must be created or changed; or when an executing agent holds a reviewer finding that would change an
docs-lookupUse when the answer depends on external docs, environment-specific operational context, or facts about the user's own setup, including devices, radios, networks, accounts, or what is installed where. Look up setup facts in the user's docs or reachable systems before asking the user. Includes discove
frontend-designGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
github-planUse when the user asks for a plan, what's next / what is next in a plan or workstream, how work fits the plan, plan direction/alignment, durable work tracking, roadmap, workstream planning, GitHub issue-backed planning, issue graphs, parent issues, sub-issues, blockers, milestones, Projects. Use dec
github-work-rollupProduce read-only GitHub work rollups and external-comment attention reports. Use for activity summaries, work digests, or finding issue/PR comments the Director may not have seen or answered.
githubComprehensive GitHub Expert persona for repository execution and hygiene: PRs, branches, Actions, reviews, merge/deploy state, issue comments, and safe cleanup. For durable planning, roadmaps, blockers, Projects, or workstream graphs, use github-plan.
google-seoUse for Google Search Console, Bing Webmaster Tools, IndexNow, PageSpeed Insights, Lighthouse, Core Web Vitals, sitemap/indexing checks, SEO performance reports, and shared search tooling setup across sites.
historyUse when the Director asks about past decisions, what was decided and when, changed or contradictory decisions, or patterns of frustration and direction friction across GitHub and local provider sessions. Do not use for ordinary current-state debugging, general historical trivia, or memory updates.
infra-opsUse for infrastructure operations across private docs, local automation, hosts, ingress, network, storage, media, and managed service APIs. Trigger for read-only inventory, health checks, guarded pilot writes, rollback/snapshot planning, admin helper routing, and production-impacting infra changes a
jetbrains-inspectionUse JetBrains inspections through isolated headless native PyCharm, IntelliJ IDEA and WebStorm workers on macOS; trigger for code changes, readiness checks, PR/push validation, IDE warnings, inspection triage, or when code quality should be driven toward zero actionable IDE findings.
launchplaneUse for Launchplane-managed product/runtime state, secrets, config, deployments, rollout direction, product ownership boundaries, merge-train flow, and audited admin mutations. Use with github-plan when Launchplane work needs to stay aligned with a durable plan, issue graph, blockers, or rollout seq
local-llmUse when the user explicitly asks about local LLMs, LM Studio, local model inventory, local model chat, local model benchmarking, model role curation, or configuring private/local model endpoints. Provides public-safe mechanics and model index guidance for locally hosted or trusted-network OpenAI-co
memory-distillationUse only when the user explicitly asks to audit, clean, prune, archive, reset, or distill Codex or Claude Code memories into skills, repo docs/issues, or local config. Never use implicitly or for ordinary repo work.
model-reviewUse when a change should be reviewed by a model from another provider, or when the user asks for a second opinion, an independent or outside review, dissent, or a Gemini, GPT, or Claude review of work. Covers shared agent instructions, approval and safety rules, destructive helpers, and contracts ot
openai-docsUse for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migrat
partdbUse when the user asks to find, organize, count, categorize, locate, or safely update components, tools, consumables, or other inventory in a Part-DB instance. Trigger for Part-DB inventory workflows, API or MCP integration choices, schema discovery, read-only stock lookup, intake planning, and prop
peopleResolve named humans, collaborators, users, reviewers, assignees, managers, clients, contacts, GitHub handles, nicknames, aliases, or likely misspellings into private local identity and contact context when identity may affect communication, routing, memory cleanup, rollout friction, GitHub planning
plugin-creatorCreate and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update re
python-uv-workflowUse for Python repo tasks involving setup, commands, scripts, tests, dependencies, lockfiles, packaging, builds, releases, PyPI/TestPyPI, or environment management. Steer toward uv and repo-defined entrypoints instead of system Python, pip, or ad hoc virtualenv commands.
repo-readinessUse when building or installing an installed or packaged app, when the user asks whether a change, branch, PR, or workstream is ready to review, merge, ship, pause, or hand off, or asks to run gates, validate changes, check CI/PR readiness, inspect IDE warnings, verify UI, or identify blockers. Orch
rollout-frictionUse only when the user explicitly asks to audit rollout/session files, runout files, session traces, or agent workflow friction. Never use implicitly or for ordinary debugging.
security-reviewUse only when the user explicitly requests security work such as a security review, audit, threat model, secure-by-default guidance, auth/authorization review, secrets check, tenant isolation review, webhook safety review, supply-chain/release risk review, or asks whether code is safe from a securit
skill-creatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
supervisorUse to hand implementation work to a separate agent process on any provider, including headless CLI handoffs, through the supported launcher; or when the Director asks a session to supervise other sessions for a stretch of work or take over a Supervisor handoff. Full supervision groups related work,
upstream-convergenceUse when asked to update, refresh, synchronize, converge, or forward-port a maintained downstream fork against its upstream repository, including recurring upstream snapshot integrations and guarded fork cutovers. Do not use for an ordinary feature-branch merge, a one-off cherry-pick, or discussion
work-closeoutUse when the user requests a native reminder, including plain repeating reminders or reminders to return to an exact Codex or Claude Code session or start a repository check-in, or asks to wrap up, clean up, close out, pause, park, hand off, determine what remains before stopping, preserve plan dire
Hooks (13)
- PreToolUse
uv run --quiet "${CLAUDE_PLUGIN_ROOT}/hooks/command_policy_hook.py" --json || true
- PostToolUse
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- SessionStart
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/direction_check_hook.py" --runtime-catchup
- SessionStart
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/direction_check_hook.py" --skills-only
- UserPromptSubmit
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/direction_check_hook.py" --turn
- UserPromptSubmit
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- Stop
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- StopFailure
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- Notification
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- PermissionRequest
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- SubagentStart
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- SubagentStop
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
- SessionEnd
uv run --quiet --no-python-downloads "${CLAUDE_PLUGIN_ROOT}/hooks/session_alert_hook.py" || true
Maintain shared?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.