A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
Intelligent Linux system assistant for Cinnamon-based desktops. Directive-based workflows for security hardening, system updates, GPU management, desktop customization, performance tuning, and troubleshooting.
38 engineering discipline skills for Claude Code & OpenAI Codex — research, quality gates, testing patterns, deployment, learning, gap analysis, spec sync, and more. Extracted from real-world development.
Zero-dependency lint & format orchestrator over MCP — one pure-Rust binary wrapping ruff/oxc/taplo/rumdl and more as in-process backends, plus a tree-sitter generic tier for everything else. Exposes lint/format/cache tools with structured JSON output.
Indexed cross-repo search and AI-assisted planning for your org's codebase: search, grep, and file-find across every repo without cloning, plus a guided planning workflow that lets your team collaborate on plans together in Baz.
Static correctness linter and quality orchestrator for Claude Code plugins, skills, and hooks. Catches invalid hook schemas, bad frontmatter, YAML corruption, and token inefficiency. Delegates description quality to skill-creator.
Read-only codebase investigation and code search behind one stable tool surface. Finds code by meaning or structure, traces callers, callees and blast radius, and dispatches a detective agent for deep dives. The search engine is named in project settings and is swappable.
Windows PC optimization toolkit. Full diagnostic + fix with /optimize, or targeted sub-commands: /optimize:storage, /optimize:memory, /optimize:startup, /optimize:drivers.
A bug-management workflow that connects Notion, a workspace for notes and databases, with Claude Code. It covers creating, investigating, closing, searching for, and handling recurring bugs.
Capture process logs and let your AI agent debug them. Auto-wires the trail MCP server (listsessions, getlogs) and ships a debugging skill that walks through capturing → querying → cleanup.
Enforced code intelligence for AI coding agents — a curated, LSP-backed command surface (grep, glob, sed, diagnostics) the agent can't route around.
8 27d agoA
tokens not measured
AGPL-3.0
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: