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
Long-running worker that keeps itself inside the model's smart zone. Use for multi-stage tasks (many tool calls, many files, long edits) where the context window would otherwise blow up. It measures its own context with ctxstatus, writes a handoff note at the soft block (>=50%), and stops starting new work at the hard…
Agent Claude Code
Writes and edits technical explanations and documentation in clear, natural English. Use for documentation, design proposals, README files, pull request descriptions, and explanations that need readable prose, precise definitions, and restrained formatting.
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.
Agent Claude Code
Builds one ticket end to end in its own worktree, verifies every acceptance criterion, writes the report and opens the PR (a draft in team mode) against the base setup.sh gives it. Spawned by the /orchestrate skill with a ticket path.
ProfFroggo/froggo-mission-control
Agent Claude Code
Chief orchestrator of Mission Control AI platform. Routes work to specialist agents, manages Kanban task board, triages inbox, spawns Agent Teams for parallel work. Use when: routing tasks, checking platform status, unblocking stuck work, triaging requests, coordinating parallel multi-agent execution. Agent tool is…
Agent Claude Code
Create editable, production-ready PPTX decks from clear narrative, design, and coordinate specifications.
Agent Claude Code
Use this agent when the user asks for a comprehensive product-quality push, product logic audit, simplification pass, or "make the product easier to use" work across CCJK. Examples: Context: The user wants broad product improvement rather than a single bug fix. user: "Create a teamagent to comprehensively fix issues…
wardawgmalvicious/agent-config
Agent Claude Code
Security scan specialist. Use proactively before commits, during code reviews, or when asked to audit security. Scans for hardcoded credentials, secrets, injection risks, unsafe deserialization, overly permissive config, and risky Azure/cloud patterns. Returns findings with severity and file:line refs; does not modify…
Agent Claude Code
Fresh-context adversarial verifier for fable-mode. Spawn after substantial work with the SPEC and artifact locations; it hunts for ways the work fails the spec — it does not confirm success. Returns a findings report with evidence, or an explicit "no findings" after stating what it checked.
Agent Claude Code needs its repo
Maintain and extend the {{APPNAME}} MOAB automation — add features, re-mine broken selectors, and upgrade the server. Privileged; use deliberately, not for day-to-day automation.
Agent Claude Code
Analytics and metrics specialist for GA4, Meta Pixel, Plausible, event tracking, business metrics, and monitoring with Prometheus/Grafana.
Agent Claude Code
Specialized agent for analyzing Nix code.
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Intelligently decompose a bulk task into parallel sub-tasks, execute them concurrently, and return a single aggregated result. Use this to do the same operation across many files at once. Examples: 'add tests for all handlers', 'review all API endpoints', 'add docstrings to every Python file', 'find flaky tests across…
Agent Claude Code
Use after finishing a change in this repo to check it against CODINGGUIDELINES.md's rigor tiers, the testing mandate, and COMPLETIONCHECKLIST.md before calling the work done — flags gaps, does not fix them.
JakeTRogers/my-awesome-copilot
Agent Claude Code
A specialized chat mode for analyzing and improving prompts. Every user input is treated as material for a prompt, never as a task to perform. It assesses the prompt, resolves factual gaps itself, asks the user only what it cannot look up, and generates the final improved prompt once no material ambiguity remains.
Agent Claude Code
Conflict resolver and insight generator - synthesizes all findings into coherent conclusions with meta-insights.
Agent Claude Code
Engineering Manager — designs HOW to build through engineering definitions, architecture, plans, and technical contracts. Owns engineering-level goals, prompt architecture, and QA. Use when defining mechanisms, designing architecture, creating plans, defining data contracts, auditing prompts, or evaluating technical…
Agent Claude Code
Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for testing, debugging a flaky test, increasing test coverage, writing snapshot tests, or configuring a test plan.
Agent Claude Code
Triage a stuck Ralph loop and propose either a revised fix plan, a specific question to ask the user, or a recommendation that the task is infeasible. Invoke when the Ralph circuit breaker has opened — repeated identical errors, no progress for several iterations, max iterations approaching, or a destructive action is…
Agent Claude Code
Use this agent for legal groundwork on software products - terms of service, privacy policy, GDPR/CCPA basics, cookie consent, open-source licenses, contractor agreement checklists. Returns plain-language drafts and checklists. It is not a lawyer and says when a real one is needed.
Avalon-27reg/smyslokod-starter
Agent Claude Code
A critical review assistant for plans, architecture, and code. It looks for concrete ways a proposed solution could fail.
Agent Claude Code
Database integrity auditor — queries the persistent store for incomplete enrichment, orphaned references, stuck state-machine rows, cross-tenant leaks, and invariant violations. Read-only; produces a Good/Gaps/Critical health report with example IDs, diagnostic hypotheses, and severity tiers. Run after pipeline…
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: