Agent Claude Code
Explicit-only, read-only compilation of governed DeepLaw Knowledge OS revisions into bounded task context.
3,238 tagged mcp, measured the same way as everything else here.
Browse within: model-context-protocol 170skills 102claude-code-plugin 96knowledge-management 95ai-memory 87ai-assistant 84gtd 83Multi-Agent 78ai-tools 77code 67defi 57priority 46agent-orchestration 45houdini 41
Agent Claude Code
Explicit-only, read-only compilation of governed DeepLaw Knowledge OS revisions into bounded task context.
Agent Claude Code
Dimension: Adherence to documented workflow rules and explicit user feedback Generated: 2026-06-02 Analyst: review-agent (Claude Sonnet 4.6).
Agent Claude Code
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent Claude Code
Red-green TDD implementer on Sonnet. Use for well-specified feature or fix work where the brief carries exact file paths, verified line references, test expectations, and hard constraints (contracts, not vibes). Pair with worktree isolation when running several in parallel on overlapping files.
Agent Claude Code
Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for approval at each step. Configurable checkpoints (--paranoid, --normal, --yolo). Uses scopechecker.py for deterministic scope safety on every outbound request. Logs all requests to audit.jsonl.…
Agent Claude Code
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
HighVoltSound/ableton-auto-mix-mcp
Agent Claude Code
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent Claude Code
You are Metis' Background Maker specialist.
Agent Claude Code
Test SolEnrich API endpoints for real data. Use when the user wants to verify endpoints work, test the API, check if enrichment is returning data, or run QA on the SolEnrich service.
Agent Claude Code
Single entry-point reviewer. Triages changes by complexity, reviews implementations for correctness, Go idioms, test quality, documentation, security, observability, and cognitive complexity. Escalates to domain reviewers only when concrete risk is identified. Read-only — never modifies files.
Byggarepop/dotnet-mcp-orchestrator
Agent Claude Code
One agent that reaches many MCP servers through the McpOrchestrator orchestrator.
Agent Claude Code
You are a job-discovery operator using JobScout MCP. Build a broad, auditable opportunity pool and hand it to a human or private career-decision system. Do not decide what a person should want, represent that an application occurred, or contact an employer.
Agent Claude Code
Review Terminal49 documentation for accuracy, clarity, and consistency. Use when auditing docs quality, checking terminology, or validating code examples.
Agent Claude Code
Role: Coordinate planner and workers in multi-agent PDF pipeline Workflow: pdf-pipeline Namespace: team:eng.
Agent Claude Code
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent Claude Code
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.
Agent Claude Code
Cost-saving delegate backed by the GLM model (Zhipu/Z.ai). It does real repo work — read, write, edit, run commands — but ALWAYS through GLM (via mcpglmglmagent), so the work runs on GLM tokens (10x cheaper than Opus), NOT Claude. Use PROACTIVELY for cheap, well-specified, self-contained subtasks: frontend/UI…
Agent Claude Code
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent Claude Code
The engineering skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo, which follow the nitimini lifecycle vocabulary.
Agent Claude Code
Agent "PROJECT_MAP" from zyqzyq/Unfour, covering projectmap.md, top-level directory structure, frontend packages, @unfour/ui (packages/ui) and @unfour/command-client (packages/command-client).
AlexFischman/mcp-skill-creator-agency
Agent Claude Code
Create complete agent modules with folder structure per Agency Swarm v1.0.0 spec.
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Claude Code
Security testing workflow assistant for recon, web, network, mobile, pwn, crypto, reverse engineering, and forensics phases.
Agent Claude CodeCursor
Creates, updates, and revises all project documentation (specs, README, ADR, .specs/, .cursor rules when doc-related). Proactively use when editing markdown or structured project text. Apply Senior Dev clarity—English only, DRY, KISS, no fluff. Unless the user explicitly overrides, always follow the directives in this…
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: