CRUX-Compress: Instructions file for Codex

AGENTS.md

CRUX-Compress AGENTS.md is an instructions file for Codex, OpenCode from zotoio/CRUX-Compress. It costs 1,807 tokens per session, scanned A, original, MIT.

Repository instructions for CRUX-Compress, a project that represents source code and rules in a compact notation called CRUX. They explain how agents must read, interpret, and update that notation.

In plain words
What is it for?
Following the project's agent protocol, interpreting CRUX-formatted content, making narrowly targeted updates, and escalating when user input is needed.
Why use it?
They help agents preserve the compressed representation and avoid editing protected specification files or loading source files unnecessarily.

Instructions file for CodexOpenCode

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

This is zotoio/CRUX-Compress's own configuration. It tells Codex and OpenCode how to work on CRUX-Compress 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 CRUX-Compress configures →

Reuse

Borrowing it

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

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 CRUX-Compress AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zotoio/crux-compress/agents-md.svg)](https://agentmods.dev/instructions/zotoio/crux-compress/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zotoio/crux-compress/agents-md"><img src="https://agentmods.dev/badge/instructions/zotoio/crux-compress/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,807 This file is loaded in full into every session.
When invoked 1,807 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 $0.01807 $0.01807
Opus 5 $0.00903 $0.00903
Sonnet 5 $0.00361 $0.00361
Haiku 4.5 $0.00181 $0.00181

Measured 8d ago against content hash 9a0c21711a3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

CRUX-Compress 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 · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: CRUX Notation

This repository uses CRUX notation for semantic compression. If not already loaded into context, load CRUX.md from the project root to understand the encoding symbols and decompress any CRUX-formatted content you encounter.

Repository: github.com/zotoio/CRUX-Compress

Foundational CRUX Rules (MUST FOLLOW)

  1. ALWAYS INTERPRET AND UNDERSTAND ALL CRUX RULES FIRST - At the beginning of each agent session, interpret and understand all crux notation detected in rules, and when a new rule(s) is added to context do the same for the new rule(s) immediately. Build a mental model of all rules in context that the user can ask for at any point in time that will include a visualisation.
  2. NEVER EDIT CRUX.md - The specification is read-only unless the user specifically asks you by name to edit it, at which point ask the user to confirm before proceeding
  3. DO NOT LOAD SOURCE FILES when CRUX exists - When you see ⟦CRUX:source_file ... ⟧, use the compressed CRUX content instead of loading the original source file. The CRUX version is semantically equivalent and more token-efficient.
  4. SURGICAL DIFF UPDATES - When updating a source file that has a corresponding [filename].crux.* file, you MUST also update the CRUX file with surgical diff changes to maintain synchronization.
  5. ABORT IF NO SIGNIFICANT REDUCTION - If CRUX compression does not achieve significant token reduction (target ≤20% of original), DO NOT generate the CRUX file. The source is already compact enough.
  6. PRESERVE LITERAL PATHS - When constructing paths, URIs, or tool calls from CRUX references, preserve the literal path, filename, and extension exactly as they exist in the repository.
  7. NEVER EDIT GENERATED CRUX OUTPUT - Do not edit .crux.md or .crux.mdc files directly, and do not edit files marked with generated frontmatter (generated: plus sourceChecksum: or sourceUrl:) or the banner > [!IMPORTANT] > Generated file - do not edit!
  8. EDIT THE REAL SOURCE FILE - Move edits to the underlying source file, then re-generate the derived CRUX output. For example, [name].crux.md / [name].crux.mdc should be changed by editing the real source such as [name].md. AGENTS.md itself is a source file in this repository; do not invent AGENTS.source.md.

Read the full file on GitHub · 104 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 · 104 lines · 1,807 tokens per session scan A 9a0c21711a3b

Subscribe to this mod's changes

CRUX-Compress AGENTS.md is an instructions file published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed yesterday), licensed MIT. It adds 1,807 tokens to every session, about $0.0090 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

md-feedback copilot-instructions.md

Copilot instructions for yeominux/md-feedback, covering plan review workflow, before implementing any plan, annotation types and mcp setup.

yeominux/md-feedback · 309 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

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