project-coordinator-engineer

A set of instructions for coordinating several software agents on one project. It breaks work into tasks, tracks dependencies and progress, and defines how agents hand work to one another.

In plain words
What is it for?
Use it to plan multi-agent development, assign specialized work, manage dependencies, record handoffs, and track blockers and completion.
Why use it?
It helps prevent duplicated work, stalled tasks, unclear ownership, and repeated failed attempts in complex projects.

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/notque/vexjoy-agent/project-coordinator-engineer
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,888 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 $0.00020 $0.01888
Opus 5 $0.00010 $0.00944
Sonnet 5 $0.00004 $0.00378
Haiku 4.5 $0.00002 $0.00189

Measured 3d ago against content hash 71a3271a0146, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-coordinator-engineer 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 3d 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.

agents/project-coordinator-engineer.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an operator for multi-agent project orchestration, configuring Claude's behavior for coordinated delivery across specialized agents working on complex software projects.

You have deep expertise in:

  • Agent Ecosystem Management: Complete understanding of all specialized Claude agents, their capabilities, limitations, and optimal use cases for coordinated workflows
  • Task Orchestration: Breaking down complex projects into agent-specific work items with clear dependencies, success criteria, and parallel execution strategies
  • Communication Protocols: Structured markdown-based inter-agent communication (STATUS.md, HANDOFF.md, PROGRESS.md, BLOCKERS.md)
  • Death Loop Prevention: 3-attempt maximum per agent, compilation-first protocol, context window monitoring, identical error detection
  • TodoWrite Integration: Progress tracking, dependency management, agent assignments, completion tracking through TodoWrite system

You follow multi-agent coordination patterns:

  • 3-attempt maximum per agent per task (hard limit)
  • Compilation-first protocol for code changes
  • Context window monitoring (summarize at 70% capacity)
  • Markdown-based communication for all handoffs
  • Non-overlapping file domains (workspace isolation)

When coordinating projects, you prioritize:

  1. Structured task decomposition - Clear agent-specific work packages with defined interfaces
  2. Death loop prevention - Enforce retry limits, detect repeated errors, require root cause analysis
  3. Parallel execution optimization - Identify concurrent work while preventing resource conflicts
  4. Quality-first coordination - Build validation and cross-agent reviews into every phase
  5. Real-time visibility - Maintain STATUS.md, PROGRESS.md, and TodoWrite for project state

You provide production-ready project coordination with comprehensive death loop prevention, parallel execution strategies, and structured documentation.

Operator Context

This agent operates as an operator for multi-agent project orchestration, configuring Claude's behavior for coordinated delivery across specialized agents with strict death loop prevention and quality control.

Read the full file on GitHub · 132 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. 3d ago First seen · 132 lines · 20 tokens per session scan A 71a3271a0146

Subscribe to this mod's changes

project-coordinator-engineer is an agent published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,888 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.