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.
npx agentmods add instructions/copperheadhq/copperhead/claude-mdgit clone --depth 1 https://github.com/copperheadhq/copperheadWrote 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.
[](https://agentmods.dev/instructions/copperheadhq/copperhead/claude-md)<a href="https://agentmods.dev/instructions/copperheadhq/copperhead/claude-md"><img src="https://agentmods.dev/badge/instructions/copperheadhq/copperhead/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01242 | $0.01242 |
| Opus 5 | $0.00621 | $0.00621 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
copperhead CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
copperhead — "Cursor for circuit boards": a TypeScript CLI agent that designs and edits real KiCad projects (.kicad_sch/.kicad_pcb s-expression files), keeps markdown design docs as memory, and verifies its own work with kicad-cli ERC/DRC. Apache-2.0, Node ≥ 20.
Current state: Phase 1 implemented, pending full live verification. The CLI builds and runs (init, check/verify, do, sync, create), and the offline test suite is green. Live AC-3.x integration tests run only for explicitly configured providers: API keys enable the direct OpenAI/Anthropic paths, and COPPERHEAD_TEST_CODEX=1 enables the local saved-login Codex path. See the status note at the top of openspec/changes/build-copperhead-phase-1/tasks.md for the exact split.
Sources of truth
openspec/specs/SPEC.md— the complete technical specification: product definition, architecture, CLI surface, agent loop, tool schemas, config, safety rails, and binary acceptance criteria (AC-1 … AC-7). Read this before any design or implementation work.openspec/changes/build-copperhead-phase-1/— the active change:proposal.md(what/why),design.md(decisions D1–D14 with rationale),specs/*/spec.md(seven capability delta specs with WHEN/THEN scenarios),tasks.md(implementation checklist in dependency order).
When spec-level behavior changes, update SPEC.md and the change artifacts together — the delta specs' scenarios are meant to map 1:1 onto SPEC.md's acceptance criteria.
Workflow (OpenSpec)
This repo uses OpenSpec spec-driven development. Planning artifacts are managed with the openspec CLI and the /opsx:* skills:
/opsx:apply— implement tasks from the change (check offtasks.mdas you go)/opsx:update— revise planning artifacts coherently (never edits code)/opsx:archive— archive the change when implemented; merges delta specs intoopenspec/specs/
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.
- 4d ago First seen · 56 lines · 1,242 tokens per session scan A a533dcd6c3fa
copperhead CLAUDE.md is an instructions file published in the GitHub repository copperheadhq/copperhead (56 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,242 tokens to every session, about $0.0062 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.
Other instructions, from other repositories
Lody AGENTS.md
AGENTS.md instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
autolith AGENTS.md
AGENTS.md instructions for lambda-symbolics/autolith, covering repository guidelines, purpose and sources of truth, upstream references, architectural guardrails and package policy.
senpi AGENTS.md
AGENTS.md instructions for code-yeongyu/senpi, covering senpi repository guide, mandatory execution protocols — non-negotiable, protocol 1 — explicitly requested modifications, protocol 2 — user-requested pr reviews and structure.
supercli AGENTS.md
Instructions for yashdev9274/supercli, covering agent instructions for supercode monorepo, build commands, root level commands, individual app/package commands and package-specific commands (run from package directory).
cocode AGENTS.md
AGENTS.md instructions for cocode-agency/cocode, covering agents.md, 仓库布局, 仓库边界, cocode-gui/ and cocode-tui/.
sortie copilot-instructions.md
Copilot instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).