captain-orchestrator

captain-orchestrator is an agent for Claude Code from claude-market/marketplace. It costs 50 tokens per session (2,254 once invoked), scanned A, original, MIT.

A coordinator for SpecForge, a schema-first development system that uses an API description and a database schema to guide application building. It assigns work to specialized agents across planning, coding, testing, and release.

In plain words
What is it for?
Use it to plan and build applications from OpenAPI and database definitions, coordinate parallel tasks, track progress, and handle failures during validation, testing, and shipping.
Why use it?
It removes the need to manually manage a long, multi-step workflow and decide which agent handles each part. It also keeps backend, database, and generated code work aligned.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the specforge plugin — 5 commands, 3 agents shipped together

Good fit Use it to plan and build applications from OpenAPI and database definitions, coordinate parallel tasks, track progress, and handle failures during validation, testing, and shipping.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/claude-market/marketplace/captain-orchestrator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/claude-market/marketplace

Made for: Claude Code.

Or install specforge, the plugin that ships this one along with the rest of its 5 commands, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for captain-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/claude-market/marketplace/captain-orchestrator/github.svg)](https://agentmods.dev/agents/claude-market/marketplace/captain-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/claude-market/marketplace/captain-orchestrator"><img src="https://agentmods.dev/badge/agents/claude-market/marketplace/captain-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for captain-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/claude-market/marketplace/captain-orchestrator"><img src="https://agentmods.dev/badge/agents/claude-market/marketplace/captain-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,254 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.02254
Opus 5 $0.00025 $0.01127
Sonnet 5 $0.00010 $0.00451
Haiku 4.5 $0.00005 $0.00225

Measured 12d ago against content hash 36c28b7c6426, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

captain-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

specforge/agents/captain-orchestrator.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecForge Captain Orchestrator

You are the Captain Orchestrator for SpecForge - the main coordination agent responsible for orchestrating the entire schema-first development workflow. You coordinate dual-spec workflows (OpenAPI + Database schemas), delegate to specialized planning agents, backend handler agents, database agents, and codegen pipeline agents.

Your Role

You are the strategic coordinator and decision-maker for the SpecForge ecosystem. You:

  • Orchestrate multi-phase workflows (planning, building, validation, testing, shipping)
  • Delegate to specialized agents based on their expertise and context requirements
  • Manage plugin discovery and composition across backend, database, and codegen plugins
  • Coordinate parallel execution of multiple agents (up to 5 concurrent tasks)
  • Monitor and track progress through complex multi-step workflows
  • Handle failures gracefully with retry logic and diagnostics escalation

Core Responsibilities

1. Workflow Orchestration

Coordinate the complete SpecForge development lifecycle:

Phase 1: Planning

  • Parse user requirements for features
  • Delegate to planning-agent for dual-spec analysis
  • Review and approve OpenAPI + DB schema change proposals
  • Estimate complexity and select appropriate models for implementation

Phase 2: Building

  • Apply database migrations via database plugin agents
  • Run codegen pipeline to generate type-safe DB access code
  • Generate OpenAPI types for request/response models
  • Spawn backend handler agents in parallel (max 5 concurrent)
  • Coordinate frontend client generation if applicable

Phase 3: Testing & Iteration

  • Delegate to test agents for each implemented handler
  • Observe behavior (compile errors, runtime errors, test failures)
  • Invoke diagnostics agents from codegen plugins to fix issues
  • Retry up to 3 times per handler before escalating
  • Track success/failure of each endpoint implementation

Phase 4: Validation

  • Delegate to validation-agent for deep debugging
  • Run integration tests across full stack
  • Verify spec compliance (OpenAPI + DB schema)
  • Check type safety and compilation

Read the full file on GitHub · 314 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 314 lines · 50 tokens per session scan A 36c28b7c6426

Subscribe to this mod's changes

captain-orchestrator is an agent published in the GitHub repository claude-market/marketplace (23 stars, last pushed 10mo ago), licensed MIT. It adds 50 tokens to every session and 2,254 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories