What is agent-contract CLAUDE.md?

A repository guide for agent-contract, a command-line tool that installs shared rules and checks into software projects. It explains the project’s architecture, configuration files, roles, checks, templates, and decision log.

Use it when changing agent-contract’s CLI, detection, configuration, role files, validation checks, templates, or decision records.

It gives coding agents the project context and rules needed to make changes consistently and avoid breaking its contract-based workflow.

How Semeton/agent-contract configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Semeton/agent-contract. 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/Semeton/agent-contract/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Semeton/agent-contract

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/semeton/agent-contract/claude-md/github.svg)](https://agentmods.dev/instructions/semeton/agent-contract/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/semeton/agent-contract/claude-md"><img src="https://agentmods.dev/badge/instructions/semeton/agent-contract/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/semeton/agent-contract/claude-md"><img src="https://agentmods.dev/badge/instructions/semeton/agent-contract/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,175 This file is loaded in full into every session.

When invoked 3,175 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.

Model	Per session	Once invoked
Fable 5.1	$0.03175	$0.03175
Opus 5.5	$0.01270	$0.01270
Sonnet 5.5	$0.00635	$0.00635
Haiku 4.5	$0.00317	$0.00317

Measured 4d ago against content hash c5862c1bc9ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-contract 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.

CLAUDE.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-contract — repo context for Claude Code

This is the source code for agent-contract itself — a CLI that installs a deterministic contract layer into target repos.

What it does

agent-contract init drops a .agent/ directory into any repo, plus discoverability shims (CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md). The scaffold contains:

manifest.yaml — single entrypoint
stack.yaml — auto-detected (language, framework, ORM, db, test runner, lint, formatter)
conventions.yaml — declarative engineering policy
roles/ — one YAML per role (generator, integrator, tester, debugger, documenter), each with scoped permissions
checks/ — executable shell scripts that hard-fail on violations (pre-generate, post-generate, debug-scope)
templates/ — commit, PR, debug-report
memory/runs.jsonl — run log written by agent-contract run (telemetry, not decisions; decisions.jsonl before 0.10.0)
decisions themselves live in docs/decisions/: ADRs, or repo-memory records when repo-memory.json exists

Architecture

bin/agent-contract.js       ← CLI entrypoint, no deps
lib/
  index.js                  ← programmatic API
  commands/
    init.js                 ← orchestrates detect → write plan → execute
    detect.js               ← read-only detection (json or human output)
    run.js                  ← dispatches role + task to a provider
    update.js               ← selective refresh (roles, checks, map; leaves conventions)
  detect/
    index.js                ← detector pipeline + scoring
    detectors/
      node.js               ← NestJS, Next.js, Express, Fastify, ...
      php.js                ← Laravel, Symfony, ...
      python.js             ← Django, Flask, FastAPI
      go.js, rust.js, java.js, ruby.js, dotnet.js
  learn/
    index.js                ← --learn: samples source files, infers conventions draft
  providers/
    anthropic.js            ← Anthropic provider (claude-opus-5, streaming, adaptive thinking,
                               output_config.effort, cached system prefix, count_tokens)
    openai.js               ← OpenAI provider (gpt-4o pin — see the note in the file)
    claude-code.js          ← claude CLI provider (Pro/Max, no API key)
    echo.js                 ← dry-run echo provider
  util/
    scope.js                ← role-scope parser + widening diff (JS twin of scope-lib.sh)
    yaml.js                 ← minimal hand-rolled YAML emitter (no js-yaml dep)
    fs.js                   ← idempotent file writer (create-only / merge-shim / overwrite)
    hooks.js                ← idempotent .claude/settings.json hook installer
    templates.js            ← all emitted file contents live here
test/
  smoke.js                  ← end-to-end test, gates `npm publish` via prepublishOnly

Read the full file on GitHub · 203 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.

4d ago Changed · +1 lines · +86 tokens per session c5862c1bc9ba
18d ago Changed · -3 lines · -39 tokens per session ad6f10675a0e
2mo ago First seen · 205 lines · 3,128 tokens per session scan A 2584205c80db

Subscribe to this mod's changes

agent-contract CLAUDE.md is an instructions file published in the GitHub repository Semeton/agent-contract (21 stars, last pushed 4d ago), licensed MIT. It adds 3,175 tokens to every session, about $0.0127 per session on Opus 5.5. 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.

agent-contract CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-contract CLAUDE.mdSemeton/agent-contract	Instructions file	21	4d ago	MIT	A	3,175	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-contract: Instructions file for Claude Code