Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
muratsilahtaroglu/claude-code-starter-kit
Agent Claude Code
Owner-triggered independent process & quality critic — the project's OUTSIDE EYE. Sits outside the agent team, is never spawned by the orchestrator, and questions the rules themselves; rule COMPLIANCE is /keel-audit's job, not this one's.
Agent Claude Code
Qualitative research persona. Analyzes open-ended responses, interviews, focus groups. Categorizes themes, extracts verbatims, identifies latent needs, maps archetypes and journeys. Activated by /mode:quali and /inject-open.
Agent Claude Code
Single entry point for the example-org engagement — board grooming on the example-board GitHub Project, status-report prep for the example-team mandant, and routing per rules/org/example-routing.md. Spawn for board sync, weekly status collection, or any example-org coordination that would dump too much raw output into…
Agent Claude Code
AUDIT orchestra conductor (orchestra #21). ALWAYS spawn after any high-stakes orchestra output — BUILD, AI/ML, AUTOMATION & OPS, EXECUTIVE ADVISORY, PERSONAL FINANCE, or any change to install.sh / hooks / .github/workflows / secrets. Defaults to NEEDS WORK. Requires fresh verification evidence before flipping to…
Agent Claude Code
Adversarial reviewer of finished manuscripts. Refuses to sign off on central result claims until publication-critical metrics trace back to pinned evidence (empirical checklist) AND theorem claims trace back to an empty diagnostic manifest plus either a Lean verification or an explicit unverified flag (proof…
Agent Claude Code
Audits a proposed numeric heuristic, threshold, cap, or empirical claim destined for SKILL.md or a reference file against AZIMUTH's existing evidence base. Returns citation found, [uncalibrated] tag warranted, or contradicting evidence. Read-only — never modifies SKILL.md or references. Use before any new…
fahrellgiovanny/nothing-new-under-the-sun
Agent Claude Code
There Is Nothing New Under The Sun — a read-only scouting agent. Searches existing solutions (codebase, dependencies, packages, GitHub repos, APIs, SaaS, templates) before anyone writes code. Outputs a REUSE / USE / FORK / BUY / INTEGRATE / BUILD recommendation with a required schema and evidence matrix. Uses…
Agent Claude Code
Digital R&D team orchestrator. One-command workflow launcher that detects the current phase, coordinates PM → Architect → DBA → UI Designer → Project Manager → Engineers → QA delivery, with gate approvals at each phase.
Agent Claude Code
If no ninthwave work item context is available to you (no item ID, no item specification, no work item details), you were not launched by the ninthwave orchestrator. Inform the user this agent is designed for ninthwave orchestration (nw) and stop.
Agent Claude Code
Review Forge Rust changes for correctness, architecture fit, tests, and repository conventions.
Agent Claude Code needs its repo
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.
strikersam/autonomous-ai-agency
Agent Claude Code
The Implementer agent receives a plan from the Planner and executes it step by step. It uses the WorkspaceTools (readfile, listfiles, searchcode, applydiff) to inspect context and apply file changes.
Agent Claude Code
Specialized sub-agent for SMS verification workflows. Handles full lifecycle, discovery → createorder → waitforsms → return OTP, using VirtualSMS MCP tools across 2500+ services and 145+ countries with real physical SIM cards (not VoIP).
Agent Claude Code
Use this agent when the user needs help designing, architecting, or planning new agents or workflows. This includes: Context: User wants to create a new agent system for their project. user: "I need to build an agent that monitors GitHub PRs and sends Slack notifications" assistant: "Let me use the agent-architect to…
Agent Claude Code
Transform vague feature ideas into detailed, testable requirements with user stories and acceptance criteria.
bl1nk-bot/bl1nk-agents-manager
Agent Claude Code
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.
Agent Claude Code
A read-only reference guide for developing the Teya Pro plugin and its client. It supplies project paths, technical agreements, quality checks, and release handoff details for matching Teya work profiles.
Agent Claude Code
SquadAI configuration manager. Use this agent when you need to manage the project's AI agent configuration, run governance checks, apply policy changes, or troubleshoot agent setup issues. This agent has access to all SquadAI operations via the MCP server.
Agent Claude Code
Clarion template-language specialist (Clarion 10 through 12). Use for any task involving Clarion templates (.tpl/.tpw/.tpx) — writing a new procedure/control/extension/code/group template, modifying or debugging an existing one, explaining template directives, or designing the AppGen prompt UI and embed-point wiring.…
shir-bruchim/agent-runtime-kit
Agent Claude Code
FastAPI specialist for building production APIs. Dependency injection, Pydantic v2, middleware, WebSocket, background tasks, and auth patterns. Use when building FastAPI endpoints, designing API structure, or debugging FastAPI-specific issues.
Agent Claude Code
Files Safeword's spooled retro findings to the upstream ArcadeAI/safeword tracker and drains the spool. Dispatched by safeword's stop gate with a spool path when unfiled retro drafts exist.
Agent Claude Code ✓ vendor
Writes and edits this project's wiki in response to drift events. Receives a digest of CodeRename, ManifestStale, WikiSuggestion, and CommitDrift events; verifies each against current source; writes new concept pages or edits existing ones directly via Edit/Write. Runs unattended in a fresh context — does not see the…
Agent Claude Code
CLI user experience expert specializing in error messages, styling, progress indicators, and interactive prompts.
Agent Claude Code
Consumes pre-gathered reconciliation context (all agent findings, source snippets, scope annotations), performs semantic deduplication, scope checking, and fact verification in one pass, then produces clean review findings.
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: