agent-instructions-kit: Instructions file for Codex

AGENTS.md

agent-instructions-kit AGENTS.md is an instructions file for Codex, OpenCode from malmichaels-gif/agent-instructions-kit. It costs 898 tokens per session, scanned B, original, MIT.

A set of project instructions for maintaining agent instruction files such as AGENTS.md and CLAUDE.md. It describes a TypeScript/Node.js project with checks for safety, quality, project structure, and development commands.

In plain words
What is it for?
Use it to validate or generate agent instruction files, detect a project's technology stack, run checks, and maintain the related CLI or GitHub Action.
Why use it?
It helps keep AI instructions consistent, catches risky patterns, and makes the repository's development workflow easier to follow.

Instructions file for CodexOpenCode

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

This is malmichaels-gif/agent-instructions-kit's own configuration. It tells Codex and OpenCode how to work on agent-instructions-kit 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 agent-instructions-kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to malmichaels-gif/agent-instructions-kit. 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/malmichaels-gif/agent-instructions-kit/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/malmichaels-gif/agent-instructions-kit

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 agent-instructions-kit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/malmichaels-gif/agent-instructions-kit/agents-md/github.svg)](https://agentmods.dev/instructions/malmichaels-gif/agent-instructions-kit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/malmichaels-gif/agent-instructions-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/malmichaels-gif/agent-instructions-kit/agents-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.

agentmods 80×15 button for agent-instructions-kit AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/malmichaels-gif/agent-instructions-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/malmichaels-gif/agent-instructions-kit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 898 This file is loaded in full into every session.
When invoked 898 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00898 $0.00898
Opus 5.5 $0.00359 $0.00359
Sonnet 5.5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 2mo ago against content hash 1fad19b016fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agent-instructions-kit AGENTS.md scanned grade B with 1 finding 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 2mo 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Never execute arbitrary code from user AGENTS.md files
AGENTS.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Mission

A small CLI + GitHub Action that helps repos maintain consistent, safe agent instruction files (AGENTS.md, CLAUDE.md). Lints for dangerous patterns, scores quality, and generates templates informed by Karpathy's principles and real-world data from 2,500+ repos. Deliberately simple — no over-engineering.

Stack

TypeScript / Node.js. Bundled with @vercel/ncc. Tested with Vitest. Linted with ESLint 10 (flat config).

Local dev commands

  • Install: npm install
  • Typecheck: npm run typecheck
  • Lint: npm run lint
  • Test: npm test
  • Build: npm run build
  • Run CLI locally: npm run dev -- <command>

Project structure

  • src/ — all source code (718 lines total)
    • cli.ts — CLI entry point and command routing
    • index.ts — GitHub Action entry point
    • check.ts — file validation and quality checks
    • safety.ts — safety lint rules (regex-based pattern matching)
    • score.ts — quality scoring (A-F grade, 100-point scale)
    • detect.ts — project stack auto-detection
    • discover.ts — multi-file agent config discovery
    • templates.ts — minimal and opinionated template definitions
    • types.ts — shared TypeScript interfaces
  • dist/ — bundled output (committed, checked by CI)
  • .github/workflows/ — CI, release, Dependabot

Core principles

  • Think before coding — clarify assumptions before writing code. Don't silently pick an interpretation.
  • Simplicity first — implement the simplest solution. No premature abstractions, no config options nobody will use.
  • Surgical changes — only modify what's necessary. Don't refactor surrounding code or "clean up" unrelated files.
  • Verify, don't trust — run npm test and npm run typecheck before declaring any task complete.

When to stop and ask

  • The task requires adding a new dependency
  • You're unsure which approach to take among multiple valid options
  • The change would affect the public CLI or Action interface
  • Something feels wrong or requirements seem contradictory
  • Proceed without asking for: bug fixes, test additions, documentation updates, and changes with one obvious implementation

Read the full file on GitHub · 88 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. 2mo ago First seen · 88 lines · 898 tokens per session scan B 1fad19b016fc

Subscribe to this mod's changes

agent-instructions-kit AGENTS.md is an instructions file published in the GitHub repository malmichaels-gif/agent-instructions-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 898 tokens to every session, about $0.0036 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

agent-instructions-kit AGENTS.md compared with instructions from other repositories

agent-instructions-kit AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-instructions-kit AGENTS.mdmalmichaels-gif/agent-instructions-kitInstructions file23mo agoMITB898Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode