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
Use when migrating a .NET codebase to Microsoft Agent Framework (MAF) 1.3.0. Orchestrates the full migration using specialized skills for API lookup, plan generation, CS0618 detection, and fan-out validation. Handles NuGet package updates, namespaces, executors, sessions, workflows, streaming, events, and DevUI guards.
Agent Claude Code
GitHub Actions, CI/CD workflows, and automation pipelines. Delegate when the issue involves .github/workflows/, CI configuration, or automated checks.
Agent Claude CodeCursor
Adversarial plan auditor before implementation. Use for architecture, security, dependencies, rollback, and cold-start executability of the first 3 plan tasks.
Agent Claude Code
Find step-runner keys and inputParams — search then get; never guess wire keys.
emdashcodes/claude-code-plugins
Agent Claude Code
Used after video frames have been extracted to systematically analyze visual content and generate comprehensive video summaries.
Agent Claude Code needs its repo
Use this agent when you need to review code against a YAML specification file to ensure compliance with defined standards, conventions, and best practices. This agent will examine code, identify violations, and automatically fix non-compliant code to align 100% with the specification without altering functionality.…
Agent Claude Code
A session coding agent for the Harness Engineering project. Implements one feature per session following the spec-driven pipeline, maintains clean git state, and writes handoff notes for the next session.
Agent Claude Code
Specialist for tracker synchronization. Invoked by /push-to-tracker and /sync-status. Dispatches per .forge/settings.yaml tracker.type (linear|github|notion).
Agent Claude Code
Debugging specialist for errors and test failures. Use when encountering issues.
Agent Claude Code
User-facing Research Assistant for evidence-driven paper projects, using session-selected subagent-driven or single-Agent execution within the user's authority and reporting clear results and useful deliverables.
Agent Claude Code
The autonomous architect for substantive builds. Use PROACTIVELY whenever the sponsor asks to build, design, architect, or rework a system, tool, pipeline, document, integration, or skill — anything that adds or changes a capability. It runs the full lifecycle itself (discovery interview → eval spike → design →…
Agent Claude Code
Performs comprehensive security analysis of this repository including dependencies, code patterns, secrets, and configuration.
Agent Claude Code
Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you can…
Agent Claude Code
A database-focused coding agent for designing and reviewing relational databases, which store data in linked tables. It covers PostgreSQL and excludes SQLite-specific work.
Agent Claude Code
You are an incident investigator agent. You can perform end-to-end incident investigation workflow that fetches logs and performs root cause analysis. Use when a user wants to investigate incidents, analyze job failures, fetch and analyze logs in one workflow, or debug infrastructure issues. Combines log-fetcher…
joonlab/joonlab-claudecode-setting-for-share
Agent Claude Code
An English-to-Korean translator for structured article content represented as JSON. It preserves the document's sections and code while translating text and adding a technical glossary.
Agent Claude Code
Generates an org "overview" knowledge-page body from a composed prompt (the production overview system prompt + release inputs). Used by the key-free sub-agent overview eval (tests/evals/overview-subagent flow) to exercise overview generation on the Claude Code subscription instead of the metered Anthropic API.…
Agent Claude Code
Agent "{{NAME}}" from friedbotstudio/baseline, covering operating envelope, inputs (provided by the caller), method (mandatory sequence) and constitutional constraints (binding — art. ii).
monkey1wizard/Golem-Agents-Legion
Agent Claude Code
Strict, neutral Technical Architect that reviews plans and ideas for trade-offs, over-engineering, bugs, and performance. Adversarial counterpart to the planning author — pushes back on bad decisions.
daeryundf2-prog/LAZYANTIGRAVITY
Agent Claude Code
A read-only codebase navigation agent that finds where code, files, symbols, and behavior live. It searches the workspace and reports the relevant absolute paths without editing anything.
Agent Claude Code
Use Socratic questioning to extract raw cognitive material from the user. Supports both zeroshot (cold start) and supervised (hot start) modes.
Agent Claude Code
Use when IPC or command-surface drift is possible — after adding, renaming, or removing a Tauri command, a SidecarCommand/SidecarEvent variant, or a tauri-api.ts wrapper, and before merging any branch that touched src-tauri/src/sidecar.rs, src-tauri/sidecar-opencode/src/types.ts, src-tauri/src/lib.rs, or…
Agent Claude Code
Vulnerability-hunting strategist. The main agent spawns six concurrent instances of this subagent when stuck, hitting walls, showing quit semantics, or about to ask the user "what next" during hunting. Each instance carries one of six thinking perspectives (Chainer / Skeptic / Lateral / DevPsych / Scope-Expander /…
Agent Claude Code
Orchestrator agent for software development. Analyzes user requests, creates implementation plans, delegates tasks to specialist agents (database, backend, frontend, iOS, devops, designer), and synthesizes results. Invoke this agent for any development task that requires planning, multi-component work, or coordination…
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: