854 tagged LLM, measured the same way as everything else here.
Browse within: agentic-ai 291cursor 262cli 228mcp-server 227agents 174agent 150Multi-Agent 139prompt-engineering 134agents-md 104Science 100agentic 85claude-code-plugin 81code 75knowledge-graph 71
Agent Claude Code
Reviews JSON Schema draft-07 design patterns, validation rules, schema composition, and contract adherence for agent definitions, plugin manifests, and workflow artifacts. Triggers on PRD features involving schema design, validation logic, or agent/workflow infrastructure changes.
Agent Claude Code
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
Agent Claude Code
Exploit and payload developer — writes custom exploits, reverse shells, bypasses, and PoCs for discovered vulnerabilities. Specializes in turning vulnerability findings into working attack code.
Agent Claude Code
Rust strategic architect specializing in type-driven design, domain modeling, workspace architecture, and compile-time safety patterns. Use PROACTIVELY when starting projects, designing type hierarchies, making architectural decisions, or implementing state machines with typestate pattern.
Mexregkan/claude-for-researchers
Agent Claude Code
Read-only fresh-context adversary for ONE claim of a project document. Given only the bare claim, its location and the evidence paths — never the caller's verdict — it reads the passage, the cited script / log / output and the sibling records, and returns the weakest statement the evidence supports, ranked breaks…
Agent Claude Code
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with specific files to create or modify, component designs, data flows, and a build sequence.
Agent Claude Code
IMPL agent for one gated-sprint phase in this repo — implements the phase on its own branch and reports evidence per AGENTS.md. Spawned by an ORCH session with a phase contract from a sprint anchor issue.
Agent Claude Code
A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.
Agent Claude Code
Independent reviewer for drafted job-application assets (CV + cover letter). Critiques against the job description and runs a groundedness audit. Use only via the /apply pipeline, which passes the drafts inline. Never rewrites; only critiques.
Agent Claude Code
You are a conversion-focused copywriter specializing in creating high-performing meta titles and descriptions that maximize click-through rates from search engine results pages (SERPs).
Agent Claude Code
Reviews a supplied diff against explicit repository rules from supplied rule sources. Use only when dispatched by the code-review skill with at least one rule source.
Agent Claude Code
Agent "gaia-orchestrator" from gaia-research/gaia-skill-tree, covering role, the no-code rule, exception, session stewardship and fan-out heuristic.
Agent Claude Code
Context capture and knowledge structuring specialist. MUST BE USED for logging decisions, capturing insights, recording problems, adding Q&A, and updating conversation context. Use PROACTIVELY when important information should be remembered.
Agent Claude Code
Generates and hardens the test suite — unit AND end-to-end — for a change, runs it, and validates the behavior actually works (not just that assertions pass). Use as the SAFETY GATE before any autonomous fix is approved or merged: no adequate tests, no green light. The thing that makes the autonomous loops safe.
Agent Claude Code
Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.
Agent Claude Code
Capability bench agent for low-tier (haiku-class) candidate models. Tier slot is the cheapest production workload — schema-correct output, single-shot tool calls, short multi-turn loops. NOT for content quality; that's middle tier.
Agent Claude Code
Drafts a minimal Hubzoid hub for a one-line use case. Invoked when the user wants to create a new agent.
Agent Claude CodeCursor
Code search agent for exploring any codebase. Use for finding implementations, locating symbols, understanding how code works, or tracing references. Prefer over Bash/Read for exploratory codebase search.
Agent Claude Code
Use this agent when you have created a plan (e.g., implementation plan, architecture design, refactoring strategy, feature specification) and need to validate and iteratively improve it before execution. This agent should be invoked:\n\n- After drafting any significant technical plan that will guide implementation…
Agent Claude Code
Answers ActivityPub tickets delivered to the federation inbox.
Agent Claude Code
Read-only sweep of a communication surface (Exchange mail, Telegram, the calendar, the Sentinel urgent queue) for a named counterpart or window. Returns an inline digest. Dispatched by the orchestrator patterns; never sends, never acknowledges, never marks read.
ethanolivertroy/my-agent-stuff
Agent Claude Code
Versatile review specialist for code diffs, plans, proposed solutions, codebase health, and PR/issue validation.
Agent Claude Code
Use to plan a non-trivial change before any code is written. Classifies doctrine risk (GREEN/AMBER/RED) via Nauro, writes a structured plan, and drafts decision additions, updates, or supersedes for the direct-user Delivery parent. Returns a plan and never writes project truth or edits files.
Agent Claude Code
Memory keeper — judges episodic staging day by day, promotes durable signal to long-term memory, and stamps dream state. The one brain behind the dream pipeline's remember stage.
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: