mergewarden: Instructions file for Codex

AGENTS.md

mergewarden AGENTS.md is an instructions file for Codex, OpenCode from sjh9714/mergewarden. It costs 794 tokens per session, scanned A, original, MIT.

A repository instruction file for MergeWarden, a deterministic CI firewall that checks pull requests created with AI-generated code.

In plain words
What is it for?
Developing MergeWarden with its specified install, type-check, test, lint, and build commands, while preserving its GitHub Action and analysis safeguards.
Why use it?
It records non-negotiable security, testing, architecture, and dependency rules so changes remain consistent and reviewable.

Instructions file for CodexOpenCode

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

This is sjh9714/mergewarden's own configuration. It tells Codex and OpenCode how to work on mergewarden 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 mergewarden configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sjh9714/mergewarden. 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/sjh9714/mergewarden/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sjh9714/mergewarden

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 mergewarden AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sjh9714/mergewarden/agents-md.svg)](https://agentmods.dev/instructions/sjh9714/mergewarden/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sjh9714/mergewarden/agents-md"><img src="https://agentmods.dev/badge/instructions/sjh9714/mergewarden/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 794 This file is loaded in full into every session.
When invoked 794 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 $0.00794 $0.00794
Opus 5 $0.00397 $0.00397
Sonnet 5 $0.00159 $0.00159
Haiku 4.5 $0.00079 $0.00079

Measured 8d ago against content hash b59e201911d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mergewarden 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project

This repository implements MergeWarden, a deterministic CI firewall for AI-generated pull requests.

Non-Negotiable Principles

  • Runtime analysis must not call LLMs by default.
  • The GitHub Action must not execute PR-controlled code.
  • The GitHub Action must eventually load mergewarden.yml from the PR base branch, not from the PR head branch.
  • All policy decisions must be explainable with deterministic evidence.
  • Core analysis must be independent from GitHub APIs.
  • Every rule must have fixture-based tests.
  • Prefer small, pure functions.
  • Use TypeScript strict mode.
  • Use Zod for future config and contract validation.
  • Use Vitest for tests.
  • Do not add production dependencies without updating this file and explaining why.

Commands

  • Install: pnpm install
  • Typecheck: pnpm typecheck
  • Test: pnpm test
  • Lint: pnpm lint
  • Build: pnpm build

Architecture

  • packages/core: pure analysis engine with no GitHub API dependency. It uses @noble/hashes for SHA-256 so finding IDs and policy digests stay identical in Node.js and browsers without a Node crypto shim.
  • packages/github: private API-only pull-request collection package; depends on @mergewarden/core through the workspace and exposes transport ports used by the Action and CLI. It adds no third-party production dependency.
  • packages/web: private static browser package; uses the shared core and GitHub packages to scan public PRs without a backend, token, checkout, or telemetry
  • packages/cli: public mergewarden CLI; uses the private core and GitHub packages at build time, then bundles every runtime dependency into the published executable so npm metadata has no private or workspace:* runtime dependency
  • packages/action: API-only GitHub Action wrapper package; depends on the private core and GitHub packages through the workspace and on the official @actions/core / @actions/github toolkit only to read pull request data through GitHub APIs, write bounded reports, set outputs, update the job summary, and optionally upsert a marked PR report comment without checking out or executing PR-controlled code

Read the full file on GitHub · 71 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 · 71 lines · 794 tokens per session scan A b59e201911d6

Subscribe to this mod's changes

mergewarden AGENTS.md is an instructions file published in the GitHub repository sjh9714/mergewarden (14 stars, last pushed 16d ago), licensed MIT. It adds 794 tokens to every session, about $0.0040 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

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

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

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

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

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