Agent Plugins Marketplace

Recently added

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

Aug 26, 2026

  1. dependency-audit8stars

    Evidence-first dependency auditing: runs each ecosystem's real audit tooling for CVEs, outdated packages, license obligations and supply-chain signals, and reports only tool-verified facts under TOOL-REPORTED, INFERRED and UNKNOWN evidence tiers. Obligations-based license analysis instead of a compatibility matrix, and strictly non-destructive remediation.

    Claude Code1 skill
  2. csp8stars

    Constraint Satisfaction Problems and combinatorial optimization with Google OR-Tools CP-SAT solver

    Claude Code
  3. codebase-xray8stars

    Multi-language systematic codebase X-ray analysis (Python, Java, JavaScript, TypeScript, SQL, PL/SQL, Rust) - analyzes architecture, traces data flows, detects anti-patterns, and generates structured documentation for onboarding, architecture review, or code documentation. Root of the review and documentation dependency graph: it also owns the semantic interconnect mapper (contracts / invariants / domain rules / assumptions) that team-review and codebase-mapper both consume. Concurrent-safe: every analysis is an isolated run under .deep-dive/runs/ published to a stable root mirror. The Next Steps menu wires the output into downstream documentation generators (CLAUDE.md, codebase map, interface docs) as a technical-reference backbone. Renamed from deep-dive-analysis in 2.0.0.

    Claude Code1 skill
  4. codebase-mapper8stars

    Human-readable codebase guide generator: explores unfamiliar projects, builds a structured interconnect map (contracts, invariants, domain rules, integration hot-spots) via the codebase-xray semantic-interconnect-mapper, then autonomously profiles the project (type, audience, register) and produces audience-adaptive narrative documents with Mermaid diagrams that cite the map, including a plain-language executive summary and a domain glossary so the guide is comprehensible by everyone. Includes documentation-reality drift detection in the review phase, plus standalone documentation creation, maintenance, and humanization with bottom-up code analysis. Both docs-create and docs-maintain cover 20 documentation dimensions; docs-maintain runs a structured per-dimension drift audit (added/removed/renamed/retyped) instead of generic outdated-text matching.

    Claude Code1 skill
  5. clean-code8stars

    Rewrites source code to be more readable and human-friendly without changing behavior - improves naming, removes AI boilerplate, simplifies structure, and adds clarity comments

    Claude Code
  6. business8stars

    Legal advisory, compliance document generation, and SaaS business planning - Privacy Policies, Cookie Policies, DPAs, GDPR/ePrivacy/CCPA compliance, contract review, GTM strategy, market sizing, pricing, and positioning

    Claude Code1 skill
  7. browser-extensions8stars

    Expert Firefox extension (WebExtension) developer covering Manifest V2/V3, all 51 browser.* APIs, content scripts, background scripts, native messaging, cross-browser compatibility, AMO publishing, web-ext CLI tooling, project scaffolding, and live MDN documentation lookup; includes /firefox-scaffold, /firefox-lint, /firefox-publish commands

    Claude Code1 skill
  8. app-analyzer8stars

    Comprehensive app analysis for Android (ADB) and web (Playwright MCP) - navigation mapping, competitive analysis, design system extraction, UX flow analysis, and business model intelligence

    Claude Code
  9. ai-tooling8stars

    AI development workflow - prompt engineering and optimization, and Claude Agent SDK integration guide

    Claude Code1 skill
  10. abstraction-architect8stars

    Structural entropy auditor: finds where the same concept is represented, owned, computed or implemented more than once, and what it costs when that concept changes. Seven dimensions over two evidence tracks. Knowledge track (duplicated domain knowledge, competing sources of truth, redundant representation, duplicated or derivable state) is judged by semantic identity and ownership, so two representations suffice behind a strict gate. Form track (missed unification, prior art available, abstraction fitness) is judged by recurrence, where the Rule of Three applies to missed unification only. Global mode censuses the codebase and persists a concept index; diff mode asks the same seven questions as 'introduced or aggravated by this change' and runs as the Abstraction dimension of /senior-review:team-review and /senior-review:code-review. Report-only, grounded in canonical theory (Metz, Beck, Fowler, Gross, North, DDD).

    Claude Code1 skill
  11. downbeat4stars

    Local, human-in-the-loop message bus for coordinating parallel AI coding-agent sessions on one machine

    Claude Code
  12. deja-vu1.1kstars

    deja-vu: memory for coding agents from the sessions already on your disk — Claude Code, Codex, Cursor, opencode and thirty-one more — including work from before it was installed.

    Agent Plugins1 skill1 MCP server
  13. deja-vu1.1kstars

    deja-vu memory for Codex: your own past sessions, from every coding agent on the machine, recalled before you ask.

    Codex1 skill1 MCP server
  14. deja-vu1.1kstars

    deja-vu memory for Claude Code: your own past sessions, from every coding agent on the machine, recalled before you ask.

    Claude CodeAgent Plugins1 skill1 MCP server
  15. the-3md-concept0stars

    Turn research into a three-document decision package: an evidence base, a smallest falsifiable build plan, and an expansion catalogue with reference sources.

    Claude Code1 skill
  16. engineer-agent0stars

    Automates senior software engineer tasks: PR review, Slack Q&A, ticket implementation, design doc review, and standup generation. Uses an approval queue so you stay in control.

    Claude Code21 skills
  17. leadx-mcp0stars

    LeadX MCP connector — gives Claude access to LeadX tools via the remote MCP server at mcp.leadx.in

    Claude Code1 MCP server
  18. floppy0stars

    Session ritual for agent work: durable memory, a start rite, a wrap rite, and the guards that keep them honest

    Claude Code5 skills
  19. ghostwriter1stars

    Writes and rewrites text in your own voice instead of generic AI prose, with a check and polish pass built in.

    CodexClaude Code3 skills
  20. echo-demo6stars

    Agent_Harness MCP 接入示例服务器（stdio）：echo + SQLite 数据库访问。

    Claude Code2 MCP servers
  21. engram6stars

    Persistent cross-session memory backed by Weaviate Engram. Stores each conversation turn and recalls relevant memories before Claude answers.

    Claude Code1 skill
  22. heuer-planning0stars

    Standalone Heuer planning skill: structured analytic techniques for rigorous co-planning and assumption pressure-testing.

    Codex1 skill
  23. godspeed-core0stars

    VeigaPunk Godspeed Core plugin for Codex marketplace access.

    Codex1 skill
  24. godspeed-codex-command0stars

    VeigaPunk Godspeed Codex Command plugin for Codex marketplace access.

    Codex1 skill
  25. ds4cc0stars

    Read-only guidance for discovering reviewed DS4CC plugins and installing them with Grok Build, Codex, Kimi Code, and OpenCode bootstrap after source review.

    Codex1 skill
  26. aaronplug0stars

    aaron CLI tool for Codex hosts — invoke via Bash, not as an agent.

    Codex1 skill
  27. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  28. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  29. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  30. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  31. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  32. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  33. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  34. two7stars

    two is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  35. one7stars

    one is an open-source Codex and Claude Code plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    CodexClaude Code1 skill
  36. example7stars

    example is an open-source Codex and Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

    CodexClaude Code
  37. tabularium7stars

    Venue-qualified credit-event releases rebuilt from preserved source records.

    CodexClaude Code1 skill
  38. sapheneia7stars

    AuDHD-shaped replies, audit records, issues and comments.

    CodexClaude Code1 skill
  39. probitas7stars

    Sourced counterparty lending dossiers from declared addresses, with coverage gaps kept visible.

    CodexClaude Code1 skill
  40. pandects7stars

    Executable credit laws with broken specimens and reduced counterexamples.

    CodexClaude Code1 skill
  41. lemma7stars

    Source-linked JSONL chunks from Solidity compiler inputs and Markdown documents.

    CodexClaude Code1 skill
  42. lazarus7stars

    Proof-checked historical Ethereum fixtures with exact-request replay, no live fallback, and preservation releases a stranger can check.

    CodexClaude Code1 skill
  43. janus7stars

    A conformance suite for what a contract hook may observe and change before and after a host action.

    CodexClaude Code1 skill
  44. horos7stars

    Classify a repository's token sinks with evidence and emit the reading boundary agents respect.

    CodexClaude Code1 skill
  45. hexaemeron7stars

    Receipted delivery through merge and closure, with ranked frontier, audit, fuzzing, prose, specification, debugging, hardening, telemetry and measurement skills.

    CodexClaude Code13 skills
  46. hermes7stars

    Fail-closed Solidity gas optimisation with measured Foundry evidence.

    CodexClaude Code1 skill
  47. brevitas7stars

    Evidence-preserving budgets for engineering prose.

    CodexClaude Code1 skill
  48. berean7stars

    Digest-pinned agent releases with byte-exact citations, block-bound reads and evaluated refusals.

    CodexClaude Code1 skill
  49. ariadne7stars

    Release evidence statements binding artefact digests to the record behind them.

    CodexClaude Code1 skill
  50. alexandria7stars

    Digest-bound lending-data releases with reviewed credit views and address queries.

    CodexClaude Code1 skill