Claude Code plugins

Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.

stv

claude

Spec-Trace-Verify (STV): Traced Development methodology. Interview-driven spec, vertical trace with contract tests, implementation with trace verify loop.

15 skills

2lab-ai/oh-my-claude 37

Telegram skills for AI agents on Bot API 10.3: rich and classic messages, block JSON, uploaded media, streaming AI replies, polls, HTML widgets, sticker packs, digests, reply rewriting, operator cards, Mini App launch, initData auth and UI, Stars payments, bot operations, and a capability map

15 skills

serejaris/telegram-skills 37

Local-first hybrid semantic code search with dependency graphs and cross-repo search. MCP tools and workflow skills.

12 skills · 1 MCP server

VioletCranberry/coco-search 37

Cross-harness LLM agent communication mesh — rooms, DMs, and presence

11 commands · 1 MCP server · hooks

ExaDev/agent-comms 37

Neo4j-backed agent memory: capture/recall hooks + MCP server.

5 skills · 4 commands · 1 MCP server · hooks

neo4j-labs/meta-knowledge-graph 37

adef

claude

Agentic Detection Engineering Framework — catalog onboarding, extraction-profile authoring, and FORGE lifecycle tools via adef-mcp.

9 skills · 1 agent · 1 MCP server

Nebulock-Inc/agentic-detection-engineering-framework 37

agent-bom

claudecodex

Scan MCP servers, agents and packages for CVEs, supply-chain risk and exposed credentials; check a server before you add it; plan fixes.

9 skills · 2 MCP servers

koda-ai-studio/agent-bom 37

tale-mode

claude

Discipline mode (staged planning, receipts, verify-against-source, adversarial review) + plan/kickoff commands + a plan-reviewer agent + an always-on SessionStart discipline injector + a Stop-hook autonomous loop (Layer 1, a deterministic gate) that can arm itself from a committed, content-hash-trusted .claude/tale-mode.json during a kickoff phase + a fail-closed plan-mode auto-approve for provably read-only shell (no more permission-dialog walls during investigation).

6 skills · 2 commands · 1 agent · hooks

alicicek/tale-mode 37

Fastly development tools and platform skills

10 skills

fastly/fastly-agent-toolkit 37

TI-Toolbox for AI agents: skills (usage, scripting API, domain, codebase, running pipelines) + MCP servers (read-only wiki/source/project reader; job driver for the running app).

6 skills · 2 MCP servers

idossha/TI-Toolbox 37

GeoAI-powered skills for Claude Code: inspect geospatial files, download satellite imagery, search STAC catalogs, fetch Overture Maps data, process rasters, run AI object detection, and search session logs.

8 skills

opengeos/geoai-skills 37

Keeps a team knowledge base in git as Claude Code rules, so each article loads when Claude works on matching files, every session, or on demand from a short index. Capture learnings as you work with auto-capture or on request, add docs, repos and URLs, query and prune it, and migrate a 1.x knowledge base

7 skills · hooks

charlesjones-dev/ai-agent-plugins 37

ai-seo

claudecodex

Audits a site's code for search rankings (SEO), direct answers in featured snippets and voice assistants (AEO), and citations in AI answers from ChatGPT, Perplexity, Copilot and Google AI Overviews (GEO), crawls the live site to check what search engines get, and submits new pages to Google, Bing and Brave for indexing. Catches SEO patterns LLMs still generate, applies framework-specific fixes, generates and validates JSON-LD, builds FAQ sections and question maps, and writes llms.txt

8 skills

charlesjones-dev/ai-agent-plugins 37

flutter-monaco

claudecodex

Package-specific skills and a read-only bridge reviewer for flutter_monaco.

6 skills · 1 agent

omar-hanafy/flutter_monaco 37

Core skills: ecosystem guide, skill creator, research patterns, session reflection, plugin development. Includes UserPromptSubmit hook for forced skill evaluation.

5 skills · hooks

spences10/claude-code-toolkit 37

drt

claude

Create syncs, debug failures, initialize projects, and migrate from Census/Hightouch to drt

6 skills

drt-hub/drt 37

opsmaxx

claude

Work on your own servers through the OpsMaxx desktop app: scoped per capability, approved in the app, audited.

4 skills · 1 MCP server · hooks

OpsMaxx/OpsMaxx 37

Audits a repository for security problems and saves Markdown and JSON reports that track findings across audits, plans a sandboxed audit on a stronger model that proves each finding with a failing test, scans a live site's dependencies, and sets up file-access deny rules for secrets and pnpm supply-chain hardening

5 skills · 1 agent

charlesjones-dev/ai-agent-plugins 37

Agent skills for writing SwiftUI navigation with Scaffolding: coordinators, routing, environment values, state restoration, testing.

5 skills

dotaeva/scaffolding 37

DevOps patterns: CI debugging, tech debt detection, own all failures

5 skills

spences10/claude-code-toolkit 37

legal-audit-de

claudecodex

Multi-platform plugin for systematic German/EU legal audits (DSGVO, TDDDG, UWG, AI Act, etc.). Scans codebases, live URLs, and individual legal documents. Produces severity-classified findings + clean corrected versions. NOT legal advice.

4 skills · hooks

FutureRootsDE/legal-audit-de 37

descript

claudecodex

Import media, edit with Underlord, publish share links, and export transcripts or Premiere/Resolve timelines — from your agent.

5 skills

descriptinc/descript-mcp 37

Claude Code workflow patterns: prompting, CLAUDE.md maintenance, multi-agent orchestration

4 skills

spences10/claude-code-toolkit 37

email

claude

Email management via IMAP/SMTP — multi-account

2 skills · 1 MCP server · hooks

n24q02m/email 37

cman

claudecodex

Agentic memory — search and summarize coding-agent sessions, plans, and memory across projects

2 skills · 1 MCP server

laiso/cman 37

Skills for developing and maintaining Quarkus applications

3 skills

quarkusio/skills 37

imweb-ai-toolkit

claudecodex

Connect imweb CLI guidance and the public `imweb` skill for Claude Code and Claude Desktop Cowork. Short localized aliases are supported.

1 skill · 1 command · 1 MCP server

imwebme/imweb-ai-toolkit 37

Real-time pre-execution secret and exfiltration guard for Claude Code (audit mode), with the skarn-audit skill and a local read-only MCP server (four tools, no network call, every matched value masked).

1 skill · 1 MCP server · hooks

skarn-security/agent-guard 37

Real-time pre-execution secret and exfiltration guard for Codex CLI (audit mode), with the skarn-audit skill and a local read-only MCP server (four tools, no network call, every matched value masked).

1 skill · 1 MCP server · hooks

skarn-security/agent-guard 37

design-os

claudecodex

Multi-runtime design operating system and CLI for Claude Code, OpenAI Codex, Gemini CLI, and Google Antigravity.

2 skills · 1 command

jangtrinh/design-os 37