All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 438,241 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules…
Verify every Swiss case citation in a draft against the OpenCaseLaw corpus with the ocl CLI before answering or filing; report resolved, missing, ambiguous and pinpoint status; never invent or "fix" a citation.
Install the claude-code-game-development plugin pack the way a user does, into a clean Claude Code config and a clean Grok Build home, prove every plugin validates, installs and loads its components, and keep the transcripts. Use when proving a claude-code-game-development PR's Done-when, checking that a plugin change…
Use when the user wants persistent memory across sessions, asks you to remember or recall facts, wants to search their knowledge bases, or convert documents/URLs to Markdown or JSON — all via the kit-for-ai MCP tools.
A task conductor for Claude Code: multi-agent orchestration with an enforced evidence contract, repo-specific learning, and update-safe local evolution.
★not rated 79
changed 2d agoA
tokens not measured
originalApache-2.0
Audit generic AGENTS.md, CLAUDE.md, and SKILL.md instructions for deterministic drift and model-era obsolescence candidates, then generate evidence-backed, reversible remediation prompts. Use when users ask to clean up, modernize, retire, or evaluate accumulated coding-agent instructions. Do not use it to…
Extract API endpoints from the active ClaudeChrome browser tab and save them as local artifacts. Use when the user asks to find, capture, reverse engineer, document, or generate Python scripts for endpoints used by the current tab, this page, a live website, or a user-specified browser interaction in ClaudeChrome.
Long-running agent harness with 5-layer memory architecture, GitHub integration via gh CLI, autonomous batch processing with a dedicated implementer subagent, Agent Teams with ATDD, quality-gate hooks, and 6 Agent Skills.
★not rated 79 4mo agoA
tokens not measured
originalMIT
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client. Runs locally from the pagerduty-mcp Python package. Needs 2 environment variables to run.
★not rated 79 2mo agoA
tokens not measured
originalApache-2.0archived
Canonical skillkit workflow served by the installed CLI. Read before auditing skill packs or analyzing skill usage, context cost, conflicts, coverage, and token burn.
GlobalPercent — build a global-macro-probability panel for an investment research system. Merges public probability data from prediction markets (Polymarket + Kalshi), classifies every market into macro modules (monetary policy / macro economy / AI / etc.), and shows the whole market's expected-probability state at a…
Install themed spinner verb packs for Claude Code. Fetches spinner packs directly from the awesome-claude-spinners repository and installs them into the user's settings. Use when the user wants to customize their Claude Code spinner, install spinner verbs, or change spinner themes.
Use the notion-skills CLI to manage AI agent skills from one or more Notion-backed workspace stores. Invoke when the user wants to install a skill from their team's store, publish a local skill they authored, sync installed skills, generate a new skill via their coding agent, manage Notion sources (one database per…
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: