Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
desilokesh1/antigravity-fullstack-hq
Agent Claude Code
Expert in technical writing and documentation. Use when creating READMEs, API docs, or technical documentation.
Agent Claude Code
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
Agent Claude Code
Systematic root-cause debugger. Use when investigating a failing test, a production bug, a flaky behavior, or any "this doesn't work and I don't know why" situation. Walks Phase 1 → 4 (root-cause → pattern analysis → hypothesis → minimal fix) and refuses to propose fixes before evidence is in.
Agent Claude Code needs its repo
A coordinating agent for a software-development workflow. It manages stages, delegates work to other agents, and checks whether each stage meets its quality requirements.
Agent Claude Code
Builds dependency-free vanilla HTML/CSS/JS webfont test pages inside web-tests/ — no frameworks, no build step. Based on the detected font characteristics it first asks the user which tests they want (variable-axis sliders, font-size slider, OpenType feature toggles, kerning on/off, script/language switching…
Agent Claude Code
Isolated batch agent for UX audit and strategy. Called by another workflow, or in parallel (e.g. "run heuristic, journey, and IA lenses at once"). Batch version of the ux-strategy skill — same methods (ux-methods.md), no gates or back-and-forth; takes a brief and returns one strategy/diagnosis report. Does not produce…
Agent Claude Code needs its repo
Coordinates the full video generation pipeline. Use as main session agent for multi-chapter video projects.
imamirezaei/Product-Team-Claude-Skills
Agent Claude Code
Specialized design agent. Replace with output from interview engine.
Agent Claude Code
Multi-Agent Orchestrator - Coordinate agents by projecttype + attributes and pipeline Specify->Plan->Tasks->Implement.
Agent Claude Code
Security testing workflow assistant for recon, web, network, mobile, pwn, crypto, reverse engineering, and forensics phases.
cagdasyurekli/codex-agy-worker
Agent Claude Code
Writes tests for existing behaviour. Adds and edits test files only — never touches production code. Use for coverage backfill where the bulk of the work is mechanical.
Agent Claude Code
Autonomous task executor. Use when a well-scoped task needs to be implemented end-to-end. Reads PRDs, implements code, runs tests, and commits.
rubenCodeforges/codeforges-claude-plugin
Agent Claude Code
MUST BE USED for API analysis. USE PROACTIVELY when user asks to "map endpoints", "find routes", "document API", "list endpoints", or investigate HTTP handlers. Works across frameworks (Express, FastAPI, Django, Spring, Go).
Agent Claude Code
Specialist on the three Mendix Studio Pro extensibility surfaces — Model SDK (TS/JS, offline, against Team Server only), Web Extensibility API (@mendix/extensions-api 11.10.0 GA, runs as a web extension inside Studio Pro), and C# Extensibility API (Mendix.StudioPro.ExtensionsAPI 11.8.0 beta, compiles to .dll and…
ThanhWilliamLe/ai-product-bootstrap
Agent Claude Code
PRIMARY agent. Drafts, edits, and polishes newsletter issues. Manages content calendar and style guide. Dispatch for all content work.
Agent Claude Code
A reasoning-focused coding subagent for architecture design, complex bug analysis, algorithm design, and comparing technical trade-offs.
Agent Claude Code
Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.
Agent Claude Code
Use this agent when you need to design, create, or improve UI/UX for any feature or component in the project. This includes creating or updating the Semantic Design System, generating UI designs for web or mobile, implementing components with proper design patterns, or reviewing existing UI for improvements. This…
Agent Claude Code
Score compiled child skill artifacts against compilation-checklist. Dispatch after compile-write in Phase 3.
Agent Claude Code
Read-only audit invocation for a claims-verifier pass. Carries Read, Grep, and Bash (recomputation only) and no network or write tools, so it can recompute hashes/figures over its sanctioned read set while an out-of-set write or fetch stays impossible by tool set. Spawned cold, per pass, by the claims-verifier…
Agent Claude Code
Runs and explains the @aziontech/webkit adoption flow — npx @aziontech/webkit init. Sets up deps, lint configs, pre-commit, the webkit MCP, and the Claude Code bundle in this project, idempotently.
Agent Claude Code
Systematic Python code review. Invoked before important commits.
jessefmoore/offensive-claude-code
Agent Claude Code needs its repo
Alternate pentest report renderer in "operator casebook" style — a single self-contained HTML deliverable with phosphor-green CRT aesthetic, dossier hero, executive briefing, master timeline, attack graph, per-act chapters, host grid, TTP matrix, attack chains, dead-ends, and close stamp. Coexists with the markdown…
Agent Claude Code
Implements one bounded ALTAI roadmap slice and its tests. Default working agent for roadmap PRs.
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: