copper-mcp: Instructions file for Codex

AGENTS.md

copper-mcp AGENTS.md is an instructions file for Codex, OpenCode from seunghyukchoe/copper-mcp. It costs 566 tokens per session, scanned A, original, Apache-2.0.

A set of coding instructions for CopperMCP, a local-first tool for automating printed-circuit-board design. It defines which parts handle geometry, connections, validation, and file changes, while AI can only propose or request bounded operations.

In plain words
What is it for?
It guides agents working on PCB automation, especially changes to public interfaces and board data. It covers architecture review, candidate immutability, validation, testing, documentation, and agent coordination.
Why use it?
It keeps untrusted board files, arguments, model output, and tool output inside a validated workflow. It also sets rules for preserving board revisions, tests, change logs, and decision records.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions Codex.

This is seunghyukchoe/copper-mcp's own configuration. It tells Codex and OpenCode how to work on copper-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything copper-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seunghyukchoe/copper-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/seunghyukchoe/copper-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/seunghyukchoe/copper-mcp

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 copper-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/seunghyukchoe/copper-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/seunghyukchoe/copper-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/seunghyukchoe/copper-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/seunghyukchoe/copper-mcp/agents-md/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 copper-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/seunghyukchoe/copper-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/seunghyukchoe/copper-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 566 This file is loaded in full into every session.
When invoked 566 The same file — it is already loaded in full.
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 $0.00566 $0.00566
Opus 5 $0.00283 $0.00283
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00057 $0.00057

Measured 8d ago against content hash e0cd623628e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

copper-mcp 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 8d 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Instructions

Product boundary

CopperMCP is a local-first PCB automation platform. The deterministic core owns geometry, connectivity, validation, and file mutation. AI and MCP layers may propose policy and invoke bounded operations, but must never bypass validation or apply model-generated copper directly.

Required workflow

  1. Read the closest architecture document or ADR before changing a public contract.
  2. Preserve candidate immutability and board revision checks.
  3. Treat board files, MCP arguments, model output, and external tool output as untrusted.
  4. Update CHANGELOG.md for user-visible changes.
  5. Update the relevant append-only ledger under docs/ledgers/ for decisions, risks, benchmarks, security reviews, or releases.
  6. Add or update tests before claiming a behavior works.

Agent coordination

  • Use only Codex's built-in subagent and collaboration capabilities for delegated work.
  • Do not invoke or depend on the external Orca application, CLI, runtime, or orchestration skills.
  • The primary agent creates and supervises every worker directly; nested delegation is not allowed.

Commands

  • make test: dependency-light unit tests.
  • make lint: Ruff plus the version, ledger, ADR-number, documentation-link, schema-set, CI-budget, audio-benchmark, and Circuit Intent checkers.
  • make typecheck: strict mypy.
  • make security: repository secret scan and dependency audit.
  • make build: build the source distribution and wheel.
  • make check: full release-oriented validation.

Use Python 3.11 or newer. The current reference implementation is Python; performance-critical Rust crates may be introduced only behind the stable contracts in src/copper_mcp/routing/contracts.py.

Security invariants

  • Never commit .env, credentials, private keys, customer boards, generated private candidates, or model-provider tokens.
  • Keep network transports bound to loopback by default.
  • Validate every external input at its boundary and cap file, job, model, and iteration budgets.
  • apply_candidate and apply_placement_candidate are the only surfaces that write to a user's board file. They must remain separate, explicitly authorized operations: default-off behind COPPER_MCP_ALLOW_APPLY, each requiring its own single-use token.
  • Never log board contents, credentials, prompts containing proprietary designs, or bearer tokens.

Read the full file on GitHub · 54 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. 8d ago First seen · 54 lines · 566 tokens per session scan A e0cd623628e5

Subscribe to this mod's changes

copper-mcp AGENTS.md is an instructions file published in the GitHub repository seunghyukchoe/copper-mcp (2 stars, last pushed today), licensed Apache-2.0. It adds 566 tokens to every session, about $0.0028 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens