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
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
Rijul1204/rashedul-agentic-engineering
Agent Claude Code
Runs the repo's quality gates (lint, format, typecheck, dead-code, scoped tests) and returns a concise pass/fail report. Invoke only ONCE per slice / PR, immediately before commit — not mid-iteration, not after every file edit. Before delegating, the caller should run the project's auto-formatter on touched files…
Agent Claude Code
Research the docs/ folder and related code in isolated context. Use for doc audits, sync scans, coverage checks, and deep reference lookups without polluting the main session's context window.
Agent Claude Code
Use this agent to audit documentation accuracy and git hygiene on any project. Cleans up plan files committed by mistake, verifies .gitignore coverage, checks README and CLAUDE.md accuracy against actual project state, and optionally verifies URLs match canonical domains. Examples: "Run docs-checker" — full audit "Run…
Agent Claude Code
Senior software architect for design decisions, trade-off analysis, and architectural review. Use when evaluating a design proposal, choosing between approaches, writing an ADR, reviewing system boundaries, or when /lead encounters a Complex task in Phase 0.
ChanMeng666/svg-animation-studio
Agent Claude Code
Visually verify a rendered SVG animation in chrome-devtools MCP and return a tight verdict (≤100 words). Specialized for the /svg-verify skill's isolated-context phase. Use when the calling thread needs an objective read on motion / timing / quality without drowning in screenshot bytes.
Agent Claude Code
RLM sub-LLM for segment-topics MAP. Reads ONE transcript-chunk file and returns topics + clip-worthy candidates (+ openthreads/callbacks) for that window only. Sonnet by default — topic tiling is cheap but the candidate ("most clip-worthy standalone moment") judgment is the quality-determining call Haiku under-rates.
Agent Claude Code
Use this agent to audit whether a codebase's invariants are carried by the strongest mechanism available — a type that makes the violation unrepresentable > a transaction boundary > a machine-checked property > a named example test > prose. Hunts three defect classes: invariants demoted to prose that a type could…
Agent Claude Code
Award-grade frontend ART + TECHNICAL DIRECTOR and orchestrator for the Atelier suite. Takes a single brief and returns a finished, premium, production-grade WEBSITE by running the image-first "design-then-code" pipeline across a specialist team (atelier-design-lead → atelier-build-engineer → atelier-ship-reviewer)…
stranma/claude-code-python-template
Agent Claude Code
Use this agent for Step S.6.4 - Code Review.\n\nPerforms an independent code review of the current phase's changes, checking for bugs, logic errors, security issues, and adherence to project conventions.\n\nExamples:\n\n \nContext: Step S.6.4, no external reviewer configured.\n\nuser: "Review the code changes for this…
Agent Claude Code
Validates specifications, plans, and implementations against the project constitution at .specify/memory/constitution.md.
codeverbojan/claude-code-kickstart
Agent Claude Code
Audits components and pages for WCAG 2.1 AA compliance. Checks contrast, semantics, forms, keyboard nav, and motion. Use on any UI component.
desilokesh1/antigravity-fullstack-hq
Agent Claude Code
Expert in technical writing and documentation. Use when creating READMEs, API docs, or technical documentation.
jSydorowicz21/Universal-AI-Infrustructure
Agent Claude Code
OpenAI-family cross-vendor agent — runs OpenAI's flagship coding model via codex exec (ID resolved from CROSSVENDOR in models.ts, never pinned in prose). TWO MODES set by the spawn prompt. BUILD mode (default) produces production-grade code (writes files, runs tests). AUDIT mode (read-only) is the cross-vendor…
Agent Claude Code
Agent "load-test" from kangminhyuk1111/agents, covering load test agent, configuration, initial setup interview, prerequisites and verify k6 installation.
Agent Claude Code
Code review and quality analysis specialist.
Agent Claude Code
Use after staging changes with git add, before running git commit. Reads the staged diff and drafts a Conventional Commits message that describes what actually changed. Use proactively whenever the user is about to commit.
Agent Claude Code
Hard-build lane (Opus 5) — the write lane for escalated, uncertain, or reasoning-heavy implementation and root-cause debugging. Use when a change is hard as code (gnarly logic, a non-trivial algorithm, a stubborn bug) or when the implementer (Sonnet) lane has failed the same task twice. Writes code and proves it.…
Najeebullah3124/awesome-claude-universe
Agent Claude Code
You are a senior UX Engineer with 8+ years of experience in user-centered design, specializing in creating intuitive, accessible, and engaging digital experiences. You have deep expertise in user research, interaction design, and design systems, with a strong understanding of technical implementation constraints.
Agent Claude Code
Expert documentation specialist. Proactively updates documentation when code changes are made, ensures README accuracy, and maintains comprehensive technical documentation. Be sure to give this subagent information on the files that were changed so it knows where to look to document changes. Always call this agent…
Maximumsoft-Co-LTD/claude-flightdeck
Agent Claude Code
Author zero-fix Design Docs that let a downstream implementation agent ship in one pass with no re-delegation. Target ≥500 lines for non-trivial tasks (correlates with zero post-delegation rework). Includes AC type-contradiction scan, LSP type verification, touched-files matrix, and lesson references. Use proactively…
smarks26/claude-plugin-template
Agent Claude Code
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples: Context: User wants to create a code review agent user: "Create an agent…
Agent Claude Code
Devil's advocate, red team, pre-mortem analysis. Assumes every plan has a fatal flaw and finds it. Invoke after forming a plan, before committing to a decision, or when something feels too good to be true.
Agent Claude Code
Plan and design drafter on Opus 5. The orchestrator dispatches it to author implementation plans, designs, and idea explorations as ADVISORY DRAFTS: it explores the change area (read-only), weighs alternatives, and returns a structured plan the orchestrator adjudicates against its fuller context. Default lane for…
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: