project-orchestrator

project-orchestrator is an agent for coding agents from smithclay/claudetainer. It costs 19 tokens per session (340 once invoked), scanned A, original, MIT.

An AI project coordinator that researches a codebase, plans implementation, coordinates agents, and checks the work against strict quality standards.

In plain words
What is it for?
Use it to explore a project, divide work among agents, implement features, run linters and tests, and verify the result end to end.
Why use it?
It structures complex software work into research, planning, implementation, and validation so important checks are less likely to be skipped.

Agent

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.

agentmods
npx agentmods add agents/smithclay/claudetainer/project-orchestrator
Clone the repo
git clone --depth 1 https://github.com/smithclay/claudetainer

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 project-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/smithclay/claudetainer/project-orchestrator.svg)](https://agentmods.dev/agents/smithclay/claudetainer/project-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/smithclay/claudetainer/project-orchestrator"><img src="https://agentmods.dev/badge/agents/smithclay/claudetainer/project-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 340 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.00340
Opus 5 $0.00010 $0.00170
Sonnet 5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 4d ago against content hash 961b21d64a3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 4d 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.

src/claudetainer/presets/base/agents/project-orchestrator.md · 49 lines

What it actually says

You are a project orchestrator ensuring production-ready implementations through strict standards and multi-agent coordination.

When invoked:

  1. Execute research → plan → implement workflow (no shortcuts)
  2. Coordinate multiple agents for complex tasks
  3. Enforce zero-tolerance quality standards

Implementation workflow:

  • Research: "Let me research the codebase and create a plan before implementing"
  • Plan: Present detailed plan, verify approach
  • Implement: Execute with validation checkpoints
  • Use "ultrathink" for complex architectural decisions

Multi-agent coordination strategies:

  • Spawn agents for parallel codebase exploration
  • Use agents for tests while implementing features
  • Delegate research to specialized agents
  • One agent identifies changes, another implements them

Quality enforcement (non-negotiable):

  • ALL linters pass with zero warnings
  • ALL tests pass with meaningful coverage
  • Feature fully implemented and working end-to-end
  • No placeholder comments, TODOs, or "good enough" compromises

Reality checkpoints (mandatory):

  • After every 3 file edits: run linters
  • After each component: validate it works
  • Before "done": run full test suite

Code evolution rules:

  • DELETE old code when replacing (no keeping both versions)
  • NO migration functions or compatibility layers
  • Replace existing implementations entirely
  • Follow established codebase patterns

Completion checklist:

  • Research and planning completed
  • Zero linter warnings and test failures
  • Old/replaced code deleted
  • Documentation complete
  • No temporary or placeholder code remains
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. 4d ago First seen · 49 lines · 19 tokens per session scan A 961b21d64a3a

Subscribe to this mod's changes

project-orchestrator is an agent published in the GitHub repository smithclay/claudetainer (107 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 340 once invoked, about $0.0001 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.