Agent Plugins Marketplace

Recently added

Plugins grouped by the day they were added to the directory, newest first.

Sep 19, 2026

  1. handoff0stars

    Audit session context and persist what matters for the next agent — decisions, dead ends, insights, and in-flight work

    CodexClaude Code1 skill
  2. gh-pages0stars

    Build or publish a static site on GitHub Pages — saves the site to docs/ and enables Pages from the docs/ folder on the default branch

    CodexClaude Code1 skill
  3. diagram0stars

    Generate an interactive SVG diagram (architecture, sequence, flowchart, ER) from a description

    CodexClaude Code1 skill
  4. deck0stars

    Generate a self-contained HTML slide deck from a topic — single file, dark theme, keyboard nav

    CodexClaude Code1 skill
  5. bootcamp0stars

    Spin up a swarm of expert subagents to build an interactive zero-to-hero course site on any topic — progressive modules, worked examples, exercises with solutions, checkpoints, a capstone, and progress tracking — shipped to docs/ and deployed on GitHub Pages

    CodexClaude Code1 skill
  6. actian-design-system1stars

    Actian Design System toolkit: generate wireframe flows with prototype wiring, create component briefs, propose component-scale designs as reasoned documents, audit designs, compare flows. 7 skills (with tiered generation: recognized / adapted / improvised), 10 agents, 155 tokens (3 themes, 8 collections), WCAG 2.2 AA. DS knowledge vendored from volivarii/actian-ds-knowledge.

    Claude Code7 skills
  7. ccsaver0stars

    Keeps whole-file reads and boilerplate writing out of the expensive model's context by delegating them to a cheap one-shot worker, only in the projects you plug in.

    Claude Code2 skills
  8. requirements-elicitation0stars

    Analyse PRDs and feature specs for gaps, generate clarifying questions for PMs and engineers, and assess technical risk before implementation

    CodexClaude Code1 skill
  9. prototype-spike0stars

    Turn a requirement or an unproven technique into a single self-contained HTML prototype that doubles as a design spike, rebuilt at high fidelity from the app's own source

    CodexClaude Code1 skill
  10. postmortem0stars

    Write a production-incident postmortem that reads well for humans and stays parseable by tooling: machine-read frontmatter, a numbered spine, and strict evidence rules

    CodexClaude Code1 skill
  11. platform-sre-kubernetes0stars

    SRE-focused Kubernetes specialist for production deployments: deploy to Kubernetes, review manifests, establish reliability practices

    CodexClaude Code1 skill
  12. okf-maintain0stars

    Adopt and maintain an Open Knowledge Format v0.2 documentation bundle: frontmatter, generated indexes, a fail-closed conformance check, and coverage that names every unindexed document

    CodexClaude Code1 skill
  13. human-cli0stars

    Design and evaluate command-line tools for human users: naming and grammar, interactive prompts, colour and progress output, error messages, and a 0-21 usability rubric

    CodexClaude Code1 skill
  14. farley-score0stars

    Score test quality with Dave Farley's 8 Properties of Good Tests: a weighted 0-10 Farley Index, tautology-theatre and mock anti-pattern detection, prioritised recommendations, and a Socratic coach

    CodexClaude Code2 skills
  15. doc-this0stars

    Reverse-engineer a legacy codebase into ATDD-ready, traceable specifications

    CodexClaude Code14 skills
  16. airflow-dags0stars

    Author, debug and configure Apache Airflow 3 DAGs: TaskFlow API, scheduling and assets, XCom, sensors, dynamic task mapping, and multi-layer test suites

    CodexClaude Code1 skill
  17. agent-cli0stars

    Build and evaluate command-line tools for AI agent consumption: machine-readable output, semantic exit codes, hardened input, and a 0-21 agent-friendliness rubric

    CodexClaude Code1 skill
  18. thesis-summarizer0stars

    Turn theses and research papers into self-contained, bidirectionally linked explainers.

    CodexClaude Code1 skill
  19. jev-model-router31.9kstars

    Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to the engine's built-in classifier when no key is set.

    Claude Code
  20. agents-md148.2kstars

    AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

    Claude Code
  21. schematics2stars

    Creates decentralized capability schematics — published, self-contained build specifications that remove the author from the loop entirely: once published, any builder (any LLM, any human team, any organization) can construct the capability independently, with zero coordination with the author — the spec is the only coordination mechanism. Also reverse-engineers schematics from existing implementations, maintains them as living specs, and builds schematic packages from any public GitHub repository (build <name>@<user>/<repo>).

    Claude Code1 skill
  22. claude-performance-tracker0stars

    Qualify good agent usage and compare approaches on a cost-per-successful-outcome basis (tokens, time, prompts).

    Claude Code8 skills
  23. branch-token-tracker0stars

    Attribute token spend to the task-tracker id in your git branch name.

    Claude Code1 skill
  24. centricmem-skill1stars

    Hosted CentricMem librarian: organise and retrieve Markdown memory via host MCP.

    CodexClaude CodeAgent Plugins1 skill1 MCP server
  25. captain-hook13stars

    Skills for the capt-hook declarative hook framework: bootstrap gates and nudges from a repo's conventions, and translate style guides into enforced StyleRules.

    Claude Code4 skills1 MCP server
  26. marianne0stars

    Marianne AI Compose plugin for composing scores, authoring configs, submitting scores to the conductor, debugging failed runs, and embedding Marianne behind apps.

    CodexClaude Code10 skills
  27. project-tracker1stars

    Bootstraps and keeps up to date a standard set of markdown tracking files (README, ROADMAP, STATUS, JOURNAL, CHANGELOG, CLAUDE, DECISIONS, ERRORS, BACKLOG) for projects under the scopes defined in ~/.claude/project-tracker/scopes.txt, manages GitHub repo creation, and regenerates PORTFOLIO.html.

    Claude Code1 skill
  28. devstandard0stars

    A development method for Codex and Claude Code: isolated workers, evidence-bearing PRs, clean review and green CI.

    CodexClaude Code1 skill
  29. posthog-pack1.8kstars

    Claude Code skill pack for PostHog (24 skills)

    Claude Code24 skills
  30. perplexity-pack1.8kstars

    Claude Code skill pack for Perplexity (30 skills)

    Claude Code30 skills
  31. openevidence-pack1.8kstars

    Claude Code skill pack for OpenEvidence medical AI (24 skills)

    Claude Code24 skills
  32. obsidian-pack1.8kstars

    Claude Code skill pack for Obsidian plugin development and vault management (24 skills)

    Claude Code24 skills
  33. mistral-pack1.8kstars

    Claude Code skill pack for Mistral AI (24 skills)

    Claude Code24 skills
  34. maintainx-pack1.8kstars

    Claude Code skill pack for MaintainX CMMS (24 skills)

    Claude Code24 skills
  35. lokalise-pack1.8kstars

    Claude Code skill pack for Lokalise (24 skills)

    Claude Code24 skills
  36. linear-pack1.8kstars

    Claude Code skill pack for Linear (24 skills)

    Claude Code24 skills
  37. lindy-pack1.8kstars

    Claude Code skill pack for Lindy AI (24 skills)

    Claude Code24 skills
  38. langchain-pack1.8kstars

    Claude Code skill pack for LangChain (24 skills)

    Claude Code24 skills
  39. klingai-pack1.8kstars

    Kling AI skill pack - 30 skills for AI video generation, image-to-video, text-to-video, and production workflows

    Claude Code30 skills
  40. juicebox-pack1.8kstars

    Claude Code skill pack for Juicebox (24 skills)

    Claude Code24 skills
  41. instantly-pack1.8kstars

    Claude Code skill pack for Instantly (24 skills)

    Claude Code24 skills
  42. ideogram-pack1.8kstars

    Claude Code skill pack for Ideogram (24 skills)

    Claude Code24 skills
  43. guidewire-pack1.8kstars

    Claude Code skill pack for Guidewire InsuranceSuite (24 skills)

    Claude Code24 skills
  44. groq-pack1.8kstars

    Claude Code skill pack for Groq (24 skills)

    Claude Code24 skills
  45. granola-pack1.8kstars

    Claude Code skill pack for Granola AI meeting notes (24 skills)

    Claude Code24 skills
  46. gamma-pack1.8kstars

    Claude Code skill pack for Gamma (24 skills)

    Claude Code24 skills
  47. fireflies-pack1.8kstars

    Claude Code skill pack for Fireflies.ai (24 skills)

    Claude Code24 skills
  48. firecrawl-pack1.8kstars

    Claude Code skill pack for FireCrawl (30 skills)

    Claude Code30 skills
  49. exa-pack1.8kstars

    Claude Code skill pack for Exa (30 skills)

    Claude Code30 skills
  50. evernote-pack1.8kstars

    Claude Code skill pack for Evernote (24 skills)

    Claude Code24 skills