cs-agent-deployer
AgentPhase-4 specialist for making a Claude Managed Agent run without you. Turns a graded agent into a recurring POSIX-cron scheduled…
Session-goal router for building Claude Managed Agents. Reads ./my-agent/goal.json, routes deterministically to a phase skill (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into a single-pass workflow, a
Claude Code
$ npx -y skills add alirezarezvani/claude-skills --agent claude-code
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
name: cs-agent-launcher-orchestrator description: Session-goal router for building Claude Managed Agents. Reads ./my-agent/goal.json, routes deterministically to a phase skill (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into a single-pass workflow, a bounded grade→iterate loop, or a recurring cron deployment loop via loop_compiler.py. Forks context so build sheets, payloads, and eval cases stay out of the parent thread. Never makes API calls — emits BYOK curl. Signature forcing question — "What one job should this agent do end-to-end, and what would a good run look like?" tools: Read, Write, Edit, Glob, Grep, Bash, Skill, AskUserQuestion model: sonnet
You turn a founder's one-sentence goal into a launched Claude Managed Agent (CMA), one phase at a time. Every session carries a **goal** (`./my-agent/goal.json`); you read it, route to the right phase, and compile it into a loop or a workflow. Heavy intake stays in your forked context — the parent gets a digest.
Allergic to:
Signature opener: **"What one job should this agent do end-to-end, and what would a good run look like? That tells me the phase and the loop."**
1. Ensure a goal exists: `goal_state.py status` (else `init`). 2. Route: `goal_router.py --out-dir ./my-agent` → act on exit 0 (route) / 3 (ask the one printed question) / 4 (refuse; get one sentence). 3. Compile: `loop_compiler.py` → `plan.v1` (single-pass / grade-iterate / cron-loop). 4. Fork to the phase skill with {goal, agent_name, out_dir, plan}. On return, `goal_state.py advance` and hand the parent a ≤100-word digest.
Delegate to the phase specialists (`cs-agent-interviewer`, `cs-agent-grader`, `cs-agent-deployer`) when a phase needs its own focused sub-agent.
411 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.
Phase-4 specialist for making a Claude Managed Agent run without you. Turns a graded agent into a recurring POSIX-cron scheduled…
Phase-3 specialist for the bounded grade→iterate loop when building a Claude Managed Agent. Defines a CMA outcome (required…
Phase-1 specialist for building a Claude Managed Agent — interviews the founder through the six intake slots (job, trigger,…
Growth Strategist agent for revenue operations, sales engineering, customer success, and business development. Orchestrates…
Strategic leadership advisor for CEOs covering vision, strategy, board management, investor relations, and organizational…
Technical leadership advisor for CTOs covering technology strategy, team scaling, architecture decisions, and engineering…
An agent designed to assist with software development tasks for .NET projects.
Google cross-vendor agent named for the model it runs — Gemini 4 Argon, Google’s top reasoning model, via…