Agents

Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.

elevanaltd/debate-hall-mcp

Agent Claude Code

Breakthrough synthesis creator. Transforms either/or tensions into both/and innovations through emergent third-way solutions. Door specialist for transcendent integration.

not rated 8 3mo ago A 37 tokens original Apache-2.0

the-tron

1226

markacianfrani/mcp-pattern-language

Agent Claude Code

Use this agent when creating, modifying, or reviewing REST API endpoints, routes, or HTTP layer code. This includes when adding new API endpoints, changing existing routes, updating HTTP status codes, modifying request/response schemas, or any time the API surface is being touched. Examples.

not rated 8 1y ago A 0 tokens

code-reviewer

1227

FuZhiyu/ResearchProjectTemplate

Agent Claude Code

Review analysis code for correctness and adherence to project guidelines. Focus on data integrity, merge correctness, and empirical research best practices. Check if implicit data handling (like missing values) aligns with analytical objectives.

not rated 8 9mo ago A 44 tokens

deps

1228

tartinerlabs/skills

Agent Claude Code

Autonomous supply-chain hardening. Use when you need the deps skill run as a background agent — pinning, registry flags, and CI gates. Detects the project's ecosystem.

not rated 8 +1 18d ago A 38 tokens original MIT

readability-reviewer

1229

Agent-Engineer-Master/skill-engineer

Agent Claude Code

Independent readability auditor for analytical documents. Two-phase check — Phase A (cheap regex/grep for banned tokens, internal codes, passive voice, jargon) gates Phase B (model-eval for action titles, so-what, specificity-vs-abstraction, consultantese drift). Read-only — never edits the document. Re-invoke with a…

not rated 8 2mo ago A 95 tokens original MIT

code-explorer

1230

turbyho/fw-context-mcp

Agent Claude Code

Code search and analysis across the entire firmware project. Uses fw-context index for symbol lookup, cross-references, and code explanations. Use for any code exploration — finding functions/classes, tracing call chains, understanding modules across domains (BLE, modem, CBOR, RTOS, OTA). Does not replace…

not rated 8 changed 5d ago A 78 tokens original MIT

prd-specialist

1231

TomMaSS/PRDforge

Agent Claude Code

Use this agent when you need to create or manage Product Requirements Documents using PRDforge. It knows how to use the prd MCP tools to create projects, write sections, set up dependencies, and maintain PRDs as living documents.

not rated 8 +1 5mo ago A 52 tokens

changes-review

1232

openSUSE/openSUSE-packaging-skill

Agent Claude Code

Adversarial pre-commit / pre-SR review of the WHOLE change — spec diff, patches, sources/service moves, build outcome, and the .changes entry — against the actual diff and upstream reality. Use as the final gate before committing or filing a submit request — it plays a hostile Factory reviewer hunting for the decline…

not rated 8 changed 2d ago A 84 tokens original Apache-2.0

a11y-critic

1233

zivtech/accessibility-skills

Agent Claude Code

Standalone accessibility design reviewer evaluating ARIA patterns, focus management, state communication, and multi-perspective access (screen reader, keyboard, low vision, cognitive). 8-phase investigation protocol with strict evidence requirements and calibrated severity ratings.

not rated 8 +2 changed 2d ago A 51 tokens GPL-3.0

amadeus-composer-agent

1234

amadeus-dlc/amadeus

Agent Claude Code

Workflow composer. Reads a task (prompt, scan report, or a running workflow's state), proposes the EXECUTE/SKIP stage grid that fits, and - once a human approves at the gate - authors it as scope data (front/report) or proposes pending-stage suffix flips (in-flight). Dispatched by the /amadeus orchestrator; never…

not rated 8 20d ago A 85 tokens original Apache-2.0

FORWARDER-ROLE

1236

noeltock/prompt-relay

Agent Claude Code

Implements fully-specified, mechanical coding work at low cost by forwarding it to a cheaper model running in a different vendor's CLI. Use AFTER the plan is settled and every decision is named. Returns files touched, key edits, commands run, blockers. NOT for tasks needing judgment among approaches (use coder-high)…

not rated 8 +3 changed 4d ago A 76 tokens

canva-react-converter

1237

PMDevSolutions/Aurelius

Agent Claude Code

Specialized agent for autonomous Canva-to-React component conversion. Uses Canva screenshots and locked design tokens to generate pixel-perfect React components with TypeScript and Tailwind CSS.

not rated 8 yesterday A 39 tokens original MIT

tool-developer

1238

qfoldit/UEFN-TOOLBELT

Agent Claude Code

Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.

not rated 7 13d ago A 38 tokens

business-architect

1239

viknesh20-20/claude-code-tool-kit

Agent Claude Code

Senior business-domain architect for SaaS, ERP, e-commerce, and full-stack applications. Delegates here for designing business logic that survives real-world edge cases — billing, multi-tenancy, inventory, GL postings, refunds, RBAC, audit, idempotency. Knows how Stripe, Linear, NetSuite, Shopify, and similar solve…

not rated 7 4mo ago A 76 tokens original MIT

bench-matcher

1240

SuanFishXYY/suanfish-design-system

Agent Claude Code

A task-routing and voting system that selects a changing group of specialist agents to discuss a request and agree on a result.

not rated 7 2mo ago A 297 tokens

mne-methodology-critic

1241

Exekiel179/MNE-MCP

Agent Claude Code

Independent, skeptical methodology reviewer for EEG/MEG/sEEG/ECoG/fNIRS analyses run via MNE. Dispatch it (in an isolated context) to audit the STATISTICAL and SCIENTIFIC validity of a planned or completed analysis — assumptions tested vs asserted, multiple-comparison scope and independence, circular analysis /…

not rated 7 2mo ago A 187 tokens original MIT

KevinRabun/judges

Agent Claude Code

Meta-judge that reviews pattern-based findings from all other judges to identify and dismiss false positives. Provides expert criteria for recognizing common static analysis FP patterns including string literal context, comment/docstring matches, test scaffolding, IaC template gating, and identifier-keyword collisions.

not rated 7 2mo ago A 60 tokens original MIT

distillate-compressor

1243

armelhbobdad/oh-my-skills

Agent Claude Code

Act as an information extraction and compression specialist. Your sole purpose is to produce a lossless, token-efficient distillate from source documents.

not rated 7 4mo ago A 0 tokens copy · 100% Apache-2.0

captain

1244

dmytri/shipshape

Agent Claude Code

Shipshape Captain: specification author, voyage lead, and outbound liaison. Use for voyage planning and spec-driven dispatch.

not rated 7 1mo ago A 26 tokens original 0BSD

component-scaffolder

1245

memi-design/design-sandbox

Agent Claude Code

Scaffolds shadcn-based React compositions into src/app/sandbox/page.tsx from a spec (from screenshot-decoder) or a plain brief. Use AFTER screenshot-decoder, or directly when the user gives a text-only brief.

not rated 7 today A 53 tokens original MIT

security-auditor

1246

naimkatiman/continuous-improvement

Agent Claude Code

Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

not rated 7 4d ago A 35 tokens copy · 83% MIT

hook-author

1247

steve-magne/hookstack

Agent Claude Code needs its repo

Auteur de hooks agentiques Hookstack (.claude/hooks/.mjs). Utiliser pour créer ou modifier un hook du catalogue. Maîtrise le pattern testable run()+DI, le sync vers registry.json (codesnippet dérivé), le fingerprint @hookstack, le schéma registry et la timeline. Le .mjs sur disque est la source de vérité du code.

not rated 7 2d ago A 80 tokens original MIT

taniwha-composition

1248

taniwhaai/arai

Agent Claude Code

Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…

not rated 7 28d ago A 118 tokens original Apache-2.0

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: