Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Software architecture and design pattern specialist. Use PROACTIVELY when adding new features, refactoring code, or reviewing system design. MUST BE USED for architectural decisions and major code structure changes.
Agent Claude Code
A document and plan review agent that checks whether requirements are covered, the work is practical, supported by industry or community evidence, and safe.
Agent Claude Code
Implements exactly one scoped task in one of three modes the architect names — GREEN (minimal code to pass one named failing test), REFACTOR (behavior-preserving restructure, tests stay green), or NON-BEHAVIORAL (an exact config/rename/docs edit) — then commits. Scope-locked: never exceeds the single task it was…
Agent Claude Code
A code-review agent that examines the changes shown by a Git diff, which is a summary of edits between versions.
Agent Claude Code
Use when downloading high-value candidate source URLs into project-root source/raw as one raw Markdown page per canonical URL, with minimal YAML front matter, high-level classification metadata, and ingest-list status updates. Trigger for raw webpage capture, webfetch-first source/raw downloads, scripted fetch…
Agent Claude Code
Expert Task Orchestrator, managing the end-to-end development lifecycle via an AI agent swarm.
Agent Claude Code
Specialized agent for analyzing Nix code.
Agent Claude Code
A senior-engineer agent that implements approved steps from a detailed coding plan. It may make small local adjustments needed to satisfy the plan, while staying within its subject and scope.
Agent Claude Code
Architecture and design focused code reviewer. Evaluates how changes fit into the larger system, identifies structural issues, coupling problems, and missed abstractions.
Agent Claude Code
You execute the active task for {{PROJECT}}. The planning thread has already made the design decisions; your job is to build exactly what {{TASKDOC}} specifies — no more, no less.
Agent Claude Code
Automated Developer agent for implementing features based on PRD, architecture, and sprint plan.
Agent Claude CodeCodex
Use this agent when you need to create, architect, or overhaul comprehensive documentation systems including API docs, tutorials, guides, and developer-friendly content that keeps pace with code changes.
Agent Claude Code
Read-only context-gathering planner. Discovers the codebase, asks clarifying questions, proposes an implementation plan, and iterates until the user approves.
Agent Claude Code
Senior-level .NET / C# engineer for architecture review, scaffolding, EF Core, ASP.NET Core, Blazor, and MAUI targeting .NET 8 (LTS) and .NET 10. Use for review, design, scaffolding, optimization, or migration of .NET projects, or any question that needs staff/senior-engineer level .NET judgment.
Agent Claude Code needs its repo
Verifies and maintains the integrity of a live Hermes editable-install deployment (the editable-install pattern: checked-out git branch IS the running code). Use PROACTIVELY before/after any restart, update, or dev work on the live tree, and for "is the deploy healthy", "did we drift off the integrated branch", "the…
Agent Claude Code
Atelier implementation worker. Executes an approved task packet, records amendments/candidates, validates, and commits.
hwchany0ung/claude-agent-playbook
Agent Claude Code
Use for generating README updates, API documentation, technical specs, migration guides, and developer onboarding docs. Triggered after major feature completion or API changes. Reads existing code and docs to produce accurate, up-to-date documentation.
TriangulosTecnologia/devanity-skills
Agent Claude Code
Fresh-context independent verifier for a software change. Use when the caller supplies the change contract, target identity, diff/artifacts, proof obligations, and permitted verification commands. Judge whether the current target satisfies those claims. Never edit, sequence work, accept risk, or inherit the…
ashaykubal/essential-agents-skills
Agent Claude Code
Structured quality reviewer for markdown files. Use when documentation, pipeline reports, or markdown logs need analysis for completeness, broken links, formatting, and block nesting issues.
Agent Claude CodeOpenCode
Reviews code for quality, security, architecture conformance, and test coverage before.
Agent Claude Code
A read-only fact-checking specialist for documents. Verifies factual claims (statistics, dates, company names, citations, causal assertions, etc.) against authoritative sources via web search and produces a structured report of proposed corrections with sources. Does not edit files — corrections are returned as a…
Agent Claude Code
Spawn after a work phase settles or when knowledge needs maintenance: pass work refs, changed files, and target repos. Mines decisions, maintains existing docs (delete stale, reorganize misplaced), writes updates into the right knowledge layers, commits each touched repo without pushing, and reports contradictions and…
LouisLau-art/multi-agent-skills-catalog
Agent Claude Code
A validation agent for ranking datasets, which are ordered lists of items with scores or popularity measures. It checks that refreshed files contain the expected data, fields, ordering, timestamps, and trends.
ansea09/agent-skills-and-protocols
Agent Claude Code
Use when a task needs FPF-backed reasoning, planning, review, architecture analysis, source-sensitive answers, or protocol-guided work.
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: