Claude-Project-Coordinator AGENTS.md

Claude-Project-Coordinator AGENTS.md is an instructions file for Codex, OpenCode from M-Pineapple/Claude-Project-Coordinator. It costs 353 tokens per session, scanned A, original, MIT.

Repository instructions for a Swift server that tracks Xcode and Swift projects in a local JSON knowledge base. It works through MCP, a standard way for AI tools to call external functions and exchange structured data.

In plain words
What is it for?
They guide building and testing the server, locating its knowledge base, validating allowed project paths, handling MCP communication, and following Swift 6 conventions.
Why use it?
They give contributors the required governance, privacy, logging, and Swift coding rules for this project. They also prevent project data from being committed accidentally and keep server diagnostics out of normal protocol output.

Instructions file for CodexOpenCode

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 instructions/m-pineapple/claude-project-coordinator/agents-md
Clone the repo
git clone --depth 1 https://github.com/M-Pineapple/Claude-Project-Coordinator

Made for: Codex, OpenCode.

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 Claude-Project-Coordinator AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/m-pineapple/claude-project-coordinator/agents-md.svg)](https://agentmods.dev/instructions/m-pineapple/claude-project-coordinator/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/m-pineapple/claude-project-coordinator/agents-md"><img src="https://agentmods.dev/badge/instructions/m-pineapple/claude-project-coordinator/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 353 This file is loaded in full into every session.
When invoked 353 The same file — it is already loaded in full.
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 $0.00353 $0.00353
Opus 5 $0.00177 $0.00177
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00035 $0.00035

Measured 4d ago against content hash 680bf84cd3ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Claude-Project-Coordinator AGENTS.md 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.

AGENTS.md · 45 lines

What it actually says

Claude Project Coordinator

Swift MCP server for tracking Xcode/Swift projects. Local JSON knowledge base. Complements Memory Service (project status vs conversational context). No money-path boundary. Public MIT under M-Pineapple.

Governance

Read ~/Github/cv-agent-governance/AGENTS.md first. Closest-file-wins: this file wins for repo-specific rules.

Memory namespace for this repo: dev-cpc (never reserved trading tags — see cv-agent-governance/skills/memory-tagging/SKILL.md).

Hard boundaries

  • None money-path. Still treat user project data under KnowledgeBase/projects/ and KnowledgeBase/analytics/ as private — never commit those JSON files.
  • Stdio MCP: never write diagnostics to stdout. Use CPCLog (stderr only).

Coding standards

Swift 6. Use modern-swift / swift-testing skills from the Cursor skill set. Prefer the official MCP Swift SDK over hand-rolled JSON-RPC.

Build and test

swift build -c release
swift test

Executable: .build/release/project-coordinator

Optional: CPC_KNOWLEDGE_BASE=/path/to/KnowledgeBase overrides data location.

Gotchas

  • Allowed project roots are compiled into SecurityValidator.allowedBasePaths. Rebuild after changing them.
  • Version string lives in CPCVersion (Sources/ProjectCoordinator/Version.swift). Keep mcp.json, CHANGELOG, and GitHub releases in sync with it.
  • Analytics migration is file-existence gated. Do not call a bulk remigrate on every start.
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 · 45 lines · 353 tokens per session scan A 680bf84cd3ab

Subscribe to this mod's changes

Claude-Project-Coordinator AGENTS.md is an instructions file published in the GitHub repository M-Pineapple/Claude-Project-Coordinator (47 stars, last pushed 1mo ago), licensed MIT. It adds 353 tokens to every session, about $0.0018 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.