agent-rules-kit AGENTS.md

Repository-wide instructions for agent-rules-kit, a local Python command-line tool that checks the quality of AI-agent instruction files. They define the project's boundaries and its Genesis and Always-Green working modes.

In plain words
What is it for?
Use them when developing or reviewing agent-rules-kit, including its instruction-file checks, repository workflow, redaction rules, and restrictions on network access, commands, and LLM dependencies.
Why use it?
They keep agents within the project's local-first, read-only, security-conscious workflow and prevent unsupported assumptions about the tool.

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/coderdeltalan/agent-rules-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/CoderDeltaLAN/agent-rules-kit

Made for: Codex, OpenCode.

Per session 1,112 This file is loaded in full into every session.
When invoked 1,112 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 $0.01112 $0.01112
Opus 5 $0.00556 $0.00556
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 2d ago against content hash aa963b143cdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-rules-kit 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — agent-rules-kit

Scope: this file applies repository-wide to all work in this repository, unless a more specific nested AGENTS.md exists for a subtree. Authority: explicit user instructions come first, then this AGENTS.md, then repository documentation and runbooks.

This file is mandatory for every AI assistant, coding agent, or chat working on this repository.

The repository must be handled with strict CDLAN discipline. Do not improvise a new workflow.

Current project

agent-rules-kit is a local Python CLI that diagnoses baseline quality of AI agent instruction files in repositories.

Core boundaries:

  • Local-first.
  • Read-only by default.
  • No network access in runtime behavior.
  • No LLM dependency in runtime behavior.
  • No execution of commands from analyzed repositories.
  • No security guarantees or exaggerated claims.
  • Secret-like findings must be redacted.

Operating modes

There are two different work modes.

Mode 1 — Genesis / Inception

Genesis is only for creating the project from zero before remote GitHub protection exists.

During Genesis, work on main is temporarily allowed, but only under these rules:

  • main must start clean before every mutation.
  • Create one file at a time whenever possible.
  • Before stage, the prompt/status should show exactly one untracked or modified item.
  • Stage exactly one file.
  • Review the staged diff visibly.
  • Commit that one file.
  • Return main to clean state.
  • Repeat.

Genesis pattern:

  • main clean.
  • create one file.
  • validate that file.
  • status shows one change.
  • stage exact file only.
  • staged shows one file.
  • diff staged is visible.
  • no unstaged changes.
  • commit.
  • main clean.

Allowed exception:

  • The first identity baseline may include README.md, LICENSE, and .gitignore together because they form the repository identity baseline.

Mode 2 — Always-Green

Always-Green begins only after Genesis is closed.

Genesis is closed when:

  • local main is clean;
  • local checks pass;
  • AGENTS.md exists;
  • scripts/check.sh exists and passes;
  • tests exist and pass;
  • CI exists or a documented reason explains why it does not yet exist;
  • remote is created intentionally;
  • initial push is verified;
  • main protection/ruleset is applied or explicitly tracked as a blocker.

Read the full file on GitHub · 196 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. 2d ago First seen · 196 lines · 1,112 tokens per session scan A aa963b143cdc

Subscribe to this mod's changes

agent-rules-kit AGENTS.md is an instructions file published in the GitHub repository CoderDeltaLAN/agent-rules-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,112 tokens to every session, about $0.0056 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 2026-08-31.

Related

Other instructions, from other repositories