agent-contract AGENTS.md

A set of repository rules that mechanically controls what an AI coding agent may write. It uses declared roles, allowed file paths, checks, and decision logs.

In plain words
What is it for?
Use it to enforce role-based source changes, require checks before writing, limit edits to approved paths, handle ambiguous requests, and record important decisions.
Why use it?
It prevents unapproved files or types of changes from being written and makes the agent’s responsibilities and decisions traceable.

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/semeton/agent-contract/agents-md
Clone the repo
git clone --depth 1 https://github.com/Semeton/agent-contract

Made for: Codex, OpenCode.

Per session 336 This file is loaded in full into every session.
When invoked 336 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 $0.00336 $0.00336
Opus 5 $0.00168 $0.00168
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00034 $0.00034

Measured 2d ago against content hash d94b16feff58, 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 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 2d 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 · 21 lines

What it actually says

Agent Contract — ALWAYS ACTIVE

Enforcement here is mechanical, not advisory: PreToolUse hooks read .agent/ and exit non-zero to block a write. These rules hold whether or not the prompt mentions them.

  • Declare a role before writing source. Run .agent/checks/pre-generate.sh <spec.json> <role> — it validates the spec and sets the active role. Roles: generator integrator tester reviewer debugger documenter security. No role declared → source writes are blocked.
  • Stay in your role's scope. .agent/roles/<role>.yaml lists the writable globs; an empty list means read-only.
  • Contract files are off-limits in-session.agent/roles/**, .agent/checks/**, .agent/session/active-role.txt, .claude/settings*. Change those out-of-band: a human edit or agent-contract update.
  • Fix only what was asked (refactor_policy: forbidden_unless_explicitly_approved).
  • Ask when inputs are ambiguous — do not fill in defaults.
  • Log non-trivial decisions to .agent/memory/decisions.jsonl.

Available context — read what the task needs, there is no required reading order: .agent/manifest.yaml (contract index), .agent/memory/codebase-map.md (file index), .agent/conventions.yaml (style policy), .agent/memory/handoff-*.md (prior sessions). Handoff notes are written for you by the Stop hook.

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. 2d ago First seen · 21 lines · 336 tokens per session scan A d94b16feff58

Subscribe to this mod's changes

agent-contract AGENTS.md is an instructions file published in the GitHub repository Semeton/agent-contract (21 stars, last pushed 9d ago), licensed MIT. It adds 336 tokens to every session, about $0.0017 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.

Related

Other instructions, from other repositories

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

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

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 · 5,182 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 · 4,345 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

next.js 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