Auto-wrap any Click/typer CLI as an MCP server — zero-code transformation. Supports stdio, HTTP+SSE, and Streamable HTTP transport with automatic tool discovery. Turn your Python CLI tools into MCP servers Claude Code can call directly.
Rimo Voice integration for Claude Code. Ships the rimo-cli skill so the agent can drive the rimo CLI — list/read/search meeting notes, transcripts, documents, AI Q&A, and note writes. Requires the rimo CLI on your PATH and an authenticated session (rimo auth login).
Skills for SyncPoint — AI agent coordination protocol. Setup multi-agent projects, claim resources, manage sync gates, hand off work, review checkpoints, and guard files.
★not rated 5 2mo agoA
tokens not measured
originalApache-2.0
Recall and reuse your past AI coding sessions as long-term memory. Searches the local sessionwiki index so the agent can find prior work, pull context, and trace which session wrote a file.
★not rated 5▲
+1 14d agoA
tokens not measured
originalMIT
Spec-first workflows and specialized agent roles for Claude Code. Design docs before code, structured deliberation, automatic previous-session recap on startup.
★not rated 4 1mo agoA
tokens not measured
originalMIT
The meta plugin for the agent-plus framework. Workspace bootstrap, env-var readiness, identity cache, marketplace lifecycle (install/list/update/remove/search/prefer), extensions. One call to init creates .agent-plus/; envcheck reports which sibling-plugin env vars are set (names only); refresh resolves project.
★not rated 4 1mo agoA
tokens not measured
originalMIT
One-call structured triage of a git diff — file-by-file role classification (source/test/config/doc/generated/build/fixture/migration), risk tier (low/medium/high) with reasons, public-API touch detection, co-changed-test detection, secret-risk path flagging, and aggregate stats. Replaces the 5–20 Read calls an agent…
★not rated 4 1mo agoA
tokens not measured
originalMIT
The fifth universal primitive of the agent-plus framework. Mines real Claude Code session transcripts to surface repeated tool-use patterns, scaffolds them into project-scoped Claude skills (.claude/skills/ /), audits existing skills against a quality contract, and closes the loop with a cross-source feedback ag.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Your agent said the tests pass. This checks that a test actually ran. Installing turns on two hooks: one strips the tail or grep that eats test results before a test command runs, one audits the session against git the moment it ends and warns only when something was caught. It also adds /red-handed:audit and…
★not rated 4 23d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: