Recently added
Plugins grouped by the day they were added to the directory, newest first.
Sep 3, 2026
- mermaid16stars
Create, validate, and render Mermaid diagrams
Claude Code - meme16stars
Generate memes from images: classic Impact macros, labels, and TV-subtitle captions
Claude Code1 skill - mail16stars
Apple Mail integration for reading and managing email via JXA
Claude Code1 skill - mac16stars
macOS-specific automation and system integration
Claude Code - linear16stars
Managing Linear issues, projects, and teams
Claude Code1 skill - issue16stars
Work on issues from GitHub, Linear, or GitLab
Claude Code1 skill - go16stars
Go language coding standards, best practices, and testing patterns
Claude Code - gitlab16stars
GitLab workflow best practices and glab CLI usage
Claude Code - github16stars
GitHub workflow, Actions monitoring, and rulesets management
Claude Code - git16stars
Git workflow and branching best practices
Claude Code - comments16stars
Detect AI slop code comments in a diff and steer clean comment generation
Claude Code - claude-code16stars
Meta-tools for Claude Code configuration and customization
Claude Code - bun16stars
Bun runtime patterns, bunx, shell scripting, lockfile, and testing
Claude Code1 skill - atuin16stars
Query local shell history from atuin: recent commands, usage stats, and ad-hoc SQL over the history db
Claude Code - activitywatch16stars
Query local ActivityWatch usage data: per-app time, window titles, and active vs idle spans
Claude Code - evolve-loop-skills5stars
Project-local Skill plugin for Builder subagent self-review loop (resolves --setting-sources project blocker)
Claude Code - evo5stars
Self-evolving development pipeline — 3 lean agents across 6 phases with compound discovery loop, proactive research, and strict evaluation. No external dependencies.
CodexClaude Code30 skills - pil-agent-plugin2stars
Quantitative image measurement plus optional constrained multi-view reconstruction and Blender geometry checks.
CodexClaude CodeAgent Plugins4 skills - codex-goat0stars
A stronger default for Codex CLI: six independently-invocable workflow stages, specialist role cards, and an evidence ledger that makes 'done' auditable.
Codex8 skills - harlan-agent-kit10stars
Harlan's personal agent kit - Nuxt/Vue/TS workflow tools
CodexClaude Code35 skills - praxis1stars
Workflow rules from CLAUDE.md turned into hooks and skills that actually fire
Codex - praxis1stars
Workflow rules from CLAUDE.md turned into hooks and skills that actually fire
Claude CodeAgent Plugins20 skills - siteproof0stars
Evidence-based website auditing, remediation planning, safe GitHub Fix Mode, verification, and multi-format audit/fix artifact generation.
Codex1 skill - memhub2stars
XTrace MemHub team memory in Codex: automatic session capture, situated directive recall, artifact sync, plus skills for setup, login, onboarding, artifact upload, session import, search, handoff, spec-driven development, Rulebook rule authoring (create-rule) and rules proposed from CLAUDE.md + past sessions in one run (rules-from-sessions), and PR babysitting. A rule lives in a RULEBOOK — a container with its own membership, so it reaches exactly the people that book binds; the authoring skills resolve which book it lands in and offer to create one when there is none. Run memhub:setup to verify hook routing and authentication. Current desktop builds support bundled hooks; older hosts need the user bridge. Bundled handlers defer to matching installed user bridge handlers, which require trust. Codex's own threads are not captured as your sessions: spawned subagents, guardian action-reviews and memory consolidation are recognised from the rollout's thread_source and skipped by name, while every other kind — including a product surface we have not seen, since Codex's ThreadSource type is open-ended — is captured, because refusing an unknown kind would silently and unrecoverably drop real work. Every rule fire is reported under the same namespaced session id capture uploads, so a fire is linked to the Codex session it fired in. Session ↔ PR linking: after a call that addresses GitHub (`gh pr …`, a `curl`/`gh api` REST request, or a GitHub MCP tool) whose output names exactly one pull request, a PostToolUse hook asks the backend one question and injects one instruction — a session that ran `gh pr create` — or the GitHub MCP create tool — links itself unconditionally (opening it is work the session did, and a PR has many sessions), while every other GitHub call, a hand-rolled `curl` POST included, leaves the authorship judgment to the agent, and an org with no GitHub integration is told once that connecting it is what links sessions to shipped code. The hook is stateless apart from one short-lived negative answer (an enabled org with GitHub disconnected, cached 30 minutes per credential, and never inferred from a reply that merely says the feature is off) and degrades to silence on every failure. Two skills complete it: link-pr (link this or a named session by hand — also the answer for a PR opened by a script or CI helper, which is deliberately not detected) and find-contributing-sessions (scan this machine's local session history for the sessions that wrote a PR's code, rank the candidates by the evidence that matched, and link the ones you approve). The agent records ONE work type for a pull request it links (feat, fix, chore, docs, perf, refactor, other), and only when the PR has none yet — the first label is permanent, and asking again would cost the link, not just the type. Spec workflows: spec-work guides implementation, spec-check freshly reviews changes, and spec-maintain offers local/cloud bootstrap and reviewable Git or Brain proposals through the shared spec entry point.
CodexClaude CodeAgent Plugins12 skills1 MCP server - memhub-staging2stars
MemHub staging for Codex: team memory and Rulebook hooks. Use the setup skill to verify the active hook route and credential. Repository shell commands in projectless tasks must include an explicit cd prefix when the host omits workdir. Spec workflows: spec-work guides implementation, spec-check freshly reviews changes, and spec-maintain offers local/cloud bootstrap and reviewable Git or Brain proposals through the shared spec entry point.
CodexClaude Code1 MCP server - fleet1stars
Live awareness across parallel Claude Code agents working in git worktrees of the same repo. A shared board file in the repo's common .git dir tracks what every agent is working on; hooks register each session on start, update its entry on commits and prompts, and inject sibling-agent updates into context at every turn — so agents coordinate by awareness instead of colliding. Ships /fleet:status (pretty-print the board) and /fleet:start (decompose a big task, provision worktrees with kickoff briefs, and launch a session per stream — tab or headless). Local-only: no server, no auth.
Claude Code2 skills - mathmodel-skill0stars
Autopilot and guided end-to-end delivery skill for CUMCM, MCM/ICM, and Diangong Cup, with reproducibility, review, compliance, and versioned delivery folders.
Codex1 skill - rigor0stars
Verification-first workflows for finding real bugs, fixing them at root cause, and making measured improvements. Prove-it-or-don't-report-it: every finding carries an evidence tier and a proof artifact, and fixes ship a failing-then-passing regression test fixed at root cause. v2 adds test-suite validation (flaky + mutation testing), characterization safety nets, root-cause sibling sweeps, regression bisection, and a regression guard.
Claude Code9 skills - researcher0stars
Code-grounded research workflows: ground in the codebase (or given materials), gather external knowledge, and propose improvements, design briefs, library evaluations, and new ideas. Every claim is cited and tiered; local-first with disclosed, fail-closed egress. It proposes and hands implementation to the other suites. Developer-in-the-loop.
Claude Code7 skills - privacy-opsec-suite0stars
Adaptive, multi-agent workflows for building, auditing, and operating privacy-respecting, anonymity-preserving software. Covers the anonymity threat model, anonymous sessions, Tor/proxy egress and leak prevention, metadata minimization, fingerprinting and traffic-analysis resistance, supply-chain trust, opsec hardening, privacy feature design, leak incident response, doc alignment, and an opsec PR gate. Anonymous-by-default, fail-closed, developer-in-the-loop.
Claude Code13 skills - code-ops-suite0stars
Adaptive, multi-agent engineering workflows for any codebase: audit, security/privacy threat assessment, remediation, feature discovery & build, performance, tests, dependencies, local review gates, doc alignment, onboarding, and code and concept normalization. Developer-in-the-loop, behavior-preserving, with shared conventions.
Claude Code30 skills2 MCP servers - rigor0stars
Verification-first workflows for finding real bugs, fixing them at root cause, and making measured improvements. Prove-it-or-don't-report-it: every finding carries an evidence tier and a proof artifact, and fixes ship a failing-then-passing regression test fixed at root cause. v2 adds test-suite validation (flaky + mutation testing), characterization safety nets, root-cause sibling sweeps, regression bisection, and a regression guard.
Codex9 skills - researcher0stars
Code-grounded research workflows: ground in the codebase (or given materials), gather external knowledge, and propose improvements, design briefs, library evaluations, and new ideas. Every claim is cited and tiered; local-first with disclosed, fail-closed egress. It proposes and hands implementation to the other suites. Developer-in-the-loop.
Codex7 skills - privacy-opsec-suite0stars
Adaptive, multi-agent workflows for building, auditing, and operating privacy-respecting, anonymity-preserving software. Covers the anonymity threat model, anonymous sessions, Tor/proxy egress and leak prevention, metadata minimization, fingerprinting and traffic-analysis resistance, supply-chain trust, opsec hardening, privacy feature design, leak incident response, doc alignment, and an opsec PR gate. Anonymous-by-default, fail-closed, developer-in-the-loop.
Codex13 skills - code-ops-suite0stars
Adaptive, multi-agent engineering workflows for any codebase: audit, security/privacy threat assessment, remediation, feature discovery & build, performance, tests, dependencies, local review gates, doc alignment, onboarding, and code and concept normalization. Developer-in-the-loop, behavior-preserving, with shared conventions.
Codex30 skills2 MCP servers - byoh1stars
BuildYourOwnHarness — profile → compile → install → evolve a personalized AI agent harness. Synthesis recombines vetted skills/agents by keyword under 3 safety gates.
CodexClaude Code1 skill1 MCP server - cpx0stars
CPX/OSCE 모의 표준화환자(SP) 시뮬레이터. 국시원 48개 임상표현을 바탕으로 미리 작성된 276개 케이스 카드에서 환자를 뽑아 문진·신체진찰을 연습하고 100점 배점으로 채점받습니다. 웹 기록판과 연결하면 결과가 자동으로 누적됩니다.
Claude Code2 skills - canon2stars
Automated governance, versioning, and discovery tools for Claude Code.
Claude Code50 skills - agy0stars
Antigravity ↔ Claude Code bridge for review, critique, and delegation.
Claude Code2 skills - odin-writing35stars
ODIN workflows for clear, useful technical writing.
CodexClaude Code12 skills - odin-writing-advanced35stars
Advanced ODIN workflows for substantial writing and editorial work.
CodexClaude Code6 skills - odin-web35stars
ODIN workflows for building and refining web applications.
CodexClaude Code8 skills - odin-typescript35stars
ODIN workflows for modern TypeScript development.
CodexClaude Code17 skills - odin-terraform35stars
ODIN workflows for safe Terraform infrastructure changes.
CodexClaude Code1 skill - odin-security35stars
ODIN workflows for security reviews and defensive implementation.
CodexClaude Code16 skills - odin-security-advanced35stars
Advanced ODIN workflows for threat analysis and security hardening.
CodexClaude Code39 skills - odin-run35stars
ODIN workflows for executing plans and shipping finished changes.
CodexClaude Code50 skills - odin-run-advanced35stars
Advanced ODIN workflows for complex execution and delivery.
CodexClaude Code21 skills - odin-research35stars
ODIN workflows for focused research and source-backed findings.
CodexClaude Code50 skills - odin-research-advanced35stars
Advanced ODIN workflows for deep research and evidence synthesis.
CodexClaude Code13 skills