Agents

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

story-explorer

193

uu201/character-arc

Agent Claude Code

A read-only story-project search agent that finds structured information in a novel’s project files.

not rated 600 +4 2d ago A 108 tokens original MIT

IgniteUI/igniteui-angular

Agent Claude Code

Orchestrates bug fixing for igniteui-angular. Discovers scope and root cause, routes work to specialist agents, verifies completeness. Handles edge cases, escalation, and multi-branch fixes.

not rated 599 +1 changed 1mo ago A 46 tokens

cavecrew-investigator

195

stevesolun/ctx

Agent Claude Code

Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats 60% fewer tokens than vanilla Explore. Refuses to suggest fixes.

not rated 589 23d ago A 66 tokens copy · 88% MIT

solution-diagrammer

196

HoangNguyen0403/agent-skills-standard

Agent Claude Code

Draws one evidence-grounded architecture diagram as an editable draw.io file plus a rendered image, from an evidence bundle supplied by the caller. Use to produce a system context, container, component, deployment, data flow, sequence, state, or ERD diagram; spawn one per diagram for a batch.

not rated 583 +1 changed 11d ago A 66 tokens original MIT

test-writer

198

vinilana/dotcontext

Agent Claude Code

Write comprehensive unit and integration tests.

not rated 576 3mo ago A 10 tokens original MIT

catlog22/maestro-flow

Agent Claude Code

Reviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes.

not rated 574 +3 12d ago A 43 tokens

oliver-kriska/claude-elixir-phoenix

Agent Claude Code

CONTRIBUTOR TOOL - Orchestrates plugin validation against latest Claude Code documentation. Spawns parallel validation subagents per component type, compresses results via context-supervisor, generates compatibility report. Use proactively when running /docs-check. NOT distributed as part of the plugin - only…

not rated 573 +2 changed 1mo ago A 70 tokens original MIT

muse

201

haowjy/creative-writing-skills

Agent Claude Code

Author-facing creative partner for all story work: talks through the story, plans and drafts it with the author, spawns critique, continuity, reader-sim, research and knowledge-capture lanes, and owns the verdict on each draft.

not rated 569 +15 changed today A 50 tokens original Apache-2.0

decomposer

202

RandallLiuXin/GodotMaker

Agent Claude Code

Decomposes a confirmed GDD + ROADMAP into the current tag's artifact set — PLAN.md, STRUCTURE.md, SCENES.md, DESIGN.md, TOC.md, plus appends new rows to the cross-tag ASSETS.md (and optionally project.godot tweaks). Owns sub-stage 1c of /gm-gdd. Returns only a short summary so the lead's context stays lean.

not rated 559 +1 changed 14d ago A 87 tokens

aria-hr

203

evolution-foundation/evo-nexus

Agent Claude Code

Use this agent when dealing with HR and People Operations activities. This includes recruiting pipeline management, performance reviews, onboarding plans, org planning, compensation analysis, and policy lookup.\n\nExamples:\n\n- user: "What is the status of our recruiting pipeline?"\n assistant: "I will use the Aria…

not rated 552 +3 5mo ago A 277 tokens

gs-researcher

204

cookjohn/gs-skills

Agent Claude Code

Google Scholar Research Assistant - helps with academic literature search, citation tracking, and Zotero export via Google Scholar. Use proactively when the user needs to search Google Scholar, find papers, track citations, or manage references.

not rated 544 +3 7mo ago A 48 tokens original MIT

code-reviewer

205

me2resh/apexyard

Agent Claude Code

Expert code review specialist. Reviews PRs for quality, security, and standards compliance. Use proactively after code changes or when a PR needs review.

not rated 542 changed 15d ago A 33 tokens original MIT

check

206

bahayonghang/academic-writing-skills

Agent Claude Code

Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.

not rated 541 +13 3d ago A 34 tokens

database-reviewer

207

vibeeval/vibecosystem

Agent Claude Code

PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.

not rated 539 +2 2d ago A 48 tokens original MIT

fixture-reviewer

208

phel-lang/phel-lang

Agent Claude Code needs its repo

Checks .test fixtures for drift after a compiler change.

not rated 533 changed 8d ago A 15 tokens original MIT

1c-tester

209

comol/ai_rules_1c

Agent Claude Code

1C testing agent: deploys via /deploy-and-test and verifies functionality in the 1C interface — QA MCP first, web client as fallback. For UI-test requests or verification under UITESTING, on an authorized dev/test target.

not rated 530 +8 changed 1mo ago A 54 tokens

director

210

vibe-motion/auto-motion

Agent Claude Code

Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.

not rated 529 +131 3mo ago A 0 tokens

devops-agent

211

vanzan01/claude-code-sub-agent-collective

Agent Claude Code

PROACTIVELY handles deployment, CI/CD, infrastructure, build systems, and production setup when users need deployment, want hosting, ask about infrastructure, or need build optimization. Use for any DevOps and deployment needs.

not rated 525 +3 6mo ago A 48 tokens original MIT

tester

212

iusztinpaul/designing-real-world-ai-agents-workshop

Agent Claude Code

Tester role definition for /implement-universal. Loaded by the orchestrator at the start of the Tester phase, on logic tickets only. Trusts the SWE phase's happy-path e2e excerpt (does NOT re-run the Make target), runs at most 1 adversarial break path, walks every Acceptance Criterion with concrete evidence, and emits…

not rated 521 5mo ago A 99 tokens copy · 89% MIT

analyzer

214

MagicCube/agentara

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

not rated 519 +3 6mo ago A 0 tokens

ci-fixer

215

ZaxbyHub/opencode-swarm

Agent Claude Code

Staged CI failure hunter and fixer for opencode-swarm. Triages GitHub Actions failures layer-by-layer (quality → unit → integration/dist/security/php → smoke), diagnoses root causes, applies minimal targeted fixes, verifies each fix does not mask downstream failures, and never guesses — only acts on evidence from…

not rated 517 +2 today A 72 tokens original MIT

frontend-specialist

216

Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI

Agent Claude Code

Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.

not rated 512 +2 4mo ago A 63 tokens

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: