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.

agent-contract CLAUDE.md — Instructions file for coding agents by Semeton: A repository guide for agent-contract, a command-line tool that…

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/semeton/agent-contract/claude-md

Clone the repo

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

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.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.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,128 This file is loaded in full into every session.

When invoked 3,128 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.

Model	Per session	Once invoked
Fable 5	$0.03128	$0.03128
Opus 5	$0.01564	$0.01564
Sonnet 5	$0.00626	$0.00626
Haiku 4.5	$0.00313	$0.00313

Measured 4d ago against content hash 2584205c80db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 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/decisions.jsonl — append-only decision log

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 · 205 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 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 10d ago), licensed MIT. It adds 3,128 tokens to every session, about $0.0156 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.

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

agent-contract CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

agent-contract — repo context for Claude Code

What it does

Architecture

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

codex AGENTS.md

langchain AGENTS.md

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

next.js AGENTS.md