42,376
stars
+33
4,476
forks
314
watchers
355
prs
146
issues
0
releases
36
discussions
README
Plugins, agents, and skills for AI coding tools Use one collection of plugins, agents, skills, and commands across Claude Code, OpenAI Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi. A harness is the coding tool that loads and runs the components. Contributors write each component once, in Markdown, in the Claude Code plugin format. Adapters under tools/adapters/ generate the format each harness reads, map model aliases to that harness's models, and translate tool permissions where the harness supports them. CI regenerates the artifacts for every harness, validates them, and runs the OpenCode, Antigravity CLI, and Pi artifacts through their installed CLIs. The capability matrix lists what each harness supports, and ARCHITECTURE.md describes the design. The catalog contains 94 plugins, including 92 local plugins and 2 external entries. The local source contains 202 agents, 185 skills, and 105 commands. Plugins cover Python and JavaScript development, code review, testing, infrastructure, security, and other work. Multi-harness support Choose the harness you use and follow its setup route. Available components depend on the installation route and the harness's capabilities. | Tool | Installation | Components and limits | |---|---|---| | Claude Code | Plugin marketplace | Source agents, skills, and commands; plugin-specific hooks and MCP configuration | | OpenAI Codex CLI | Native marketplace or generated artifacts | Native source skills; generated TOML agents and commands as skills use a separate route | | Cursor | Plugin marketplace | Source agents, skills, and commands, with curated project rules | | OpenCode | make install-opencode | Generated agents, skills, and commands, with translated tool permissions | | Antigravity CLI | make install-antigravity | Generated plugins containing agents, skills, and commands | | GitHub Copilot | make install-copilot | Generated agent profiles and skills; commands also become invocable skills | | Pi | make install-pi | Generated skills and prompt templates; agents require a subagent extension | See the capability matrix for model mappings, tool permissions, hooks, and installation differences. For individual skills, use a skills-only installer and select your coding tool. How it works A plugin groups related agents, skills, and commands under plugins/. For example, python-development contains three agents, sixteen skills, and a scaffolding command. The chosen harness loads the installed components according to its own discovery and invocation rules. Contributors maintain one Markdown source in the Claude Code plugin format. Native registries point to that source where supported, and adapters generate the formats needed by each harness. Commands may become skills or prompt templates, and agent formats, model choices, and tool permissions vary by harness. Source agents specify model aliases such as opus, sonnet, haiku, fable, or inherit. Adapters map those aliases to each ha
Top issues
#791[FEATURE] protect-mcp hooks: run protect-mcp 0.32.1 and migrate receipt signing4 comments · 2026-10-24#813plugin-eval: cross-reference extraction ignores blockquote nesting when bounding code spans and fences1 comments · 2026-11-05
Discussions
#800Show and tell: probe-level code review records and a JSON gate0 comments · 2026-10-31#763subagent-tuner: decide the model and effort of a subagent at dispatch time0 comments · 2026-10-14#748Verifiable receipts for plugins in wshobson/agents?1 comments · 2026-10-03#723Built a diagnostic plugin from a graveyard of refuted growth tactics1 comments · 2026-09-23#599Still, I don't get fully on how to use this repo2 comments · 2026-06-25#574ccline — zsh prompt integration for the claude CLI (type shell questions, get answers and run commands)1 comments · 2026-06-10#551Global Installation?1 comments · 2026-05-24#537Case study: Running 11 AI agents as a company for 30 days1 comments · 2026-05-18