llm-safe-haven: Instructions file for Codex

AGENTS.md

llm-safe-haven AGENTS.md is an instructions file for Codex, OpenCode from pleasedodisturb/llm-safe-haven. It costs 965 tokens per session, scanned A, original, MIT.

A project instruction file for llm-safe-haven that acts as a shared working agreement for AI coding tools. It explains what belongs in AGENTS.md, a file that coding agents commonly read before editing a repository, and what remains in CLAUDE.md.

In plain words
What is it for?
Use it when an AI agent begins work on llm-safe-haven, especially before its first commit or when updating release-state information and repository agreements.
Why use it?
It makes current project state and essential rules available even in a fresh clone, without duplicating the complete coding contract.

Instructions file for CodexOpenCode

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

This is pleasedodisturb/llm-safe-haven's own configuration. It tells Codex and OpenCode how to work on llm-safe-haven 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 llm-safe-haven configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pleasedodisturb/llm-safe-haven. 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/pleasedodisturb/llm-safe-haven/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/pleasedodisturb/llm-safe-haven

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 llm-safe-haven AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pleasedodisturb/llm-safe-haven/agents-md/github.svg)](https://agentmods.dev/instructions/pleasedodisturb/llm-safe-haven/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pleasedodisturb/llm-safe-haven/agents-md"><img src="https://agentmods.dev/badge/instructions/pleasedodisturb/llm-safe-haven/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 llm-safe-haven AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pleasedodisturb/llm-safe-haven/agents-md"><img src="https://agentmods.dev/badge/instructions/pleasedodisturb/llm-safe-haven/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 965 This file is loaded in full into every session.
When invoked 965 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 $0.00965 $0.00965
Opus 5 $0.00483 $0.00483
Sonnet 5 $0.00193 $0.00193
Haiku 4.5 $0.00097 $0.00097

Measured 9d ago against content hash 27f83fe86d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llm-safe-haven 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 9d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

What this file is (and isn't)

This is the cross-agent working contract for llm-safe-haven, plus a short current-state block refreshed at ship time. Several AI coding tools — not just Claude Code — read a file named AGENTS.md at the repository root by convention before touching a project, including cloud and containerized runs that see nothing but the output of git clone.

It does not restate the full coding contract — the coding rules, the TDD contract, the project shape, or the writing style for docs. All of that lives in CLAUDE.md, cross-referenced below — this file only carries what CLAUDE.md cannot: state that changes every release, and the minimum working agreements an agent needs before its first commit (a few of which, like the hook syntax check, deliberately repeat a CLAUDE.md rule so a non-Claude agent sees them without reading it).

Why this shape (D-08)

Three options were weighed for making project state reachable from a bare clone:

  • A contract with no current-state block. Rejected — a static contract that never states where the project actually is rots exactly the way the version references in CLAUDE.md once did: nothing forces it to stay current, and the drift goes undetected until an agent trusts a stale line.
  • Un-ignoring the local session-handoff log wholesale. Rejected — that log is a verbose local working record that today carries absolute local paths, a machine name, and internal-tooling field names. Publishing it as-is would leak that content into a public repository, and every future regeneration would need re-sanitising, forever, to stay safe to publish.
  • This file: a tracked contract plus a short, guard-enforced current-state block. Chosen. It duplicates nothing from CLAUDE.md, and the one thing that must not silently go stale — the version line below — is graded by the documentation-drift guard's existing version check, not left to memory or convention alone.

No .claude/rules/ directory exists in this repository, and none is created by this change. Nothing belongs there that CLAUDE.md does not already hold; adding an empty scaffold to satisfy a convention would itself be the kind of drift-prone duplication this file exists to avoid.

Read the full file on GitHub · 67 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. 9d ago First seen · 67 lines · 965 tokens per session scan A 27f83fe86d07

Subscribe to this mod's changes

llm-safe-haven AGENTS.md is an instructions file published in the GitHub repository pleasedodisturb/llm-safe-haven (5 stars, last pushed 2d ago), licensed MIT. It adds 965 tokens to every session, about $0.0048 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

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

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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens