claude-code-rust: Instructions file for Codex

AGENTS.md

claude-code-rust AGENTS.md is an instructions file for Codex, OpenCode from srothgan/claude-code-rust. It costs 2,686 tokens per session, scanned A, original, Apache-2.0.

A repository instruction document for the claude-code-rust project. It tells coding agents how to inspect code, discuss options, make focused changes, and verify their work.

In plain words
What is it for?
Use it to guide implementation, design discussions, clarification questions, documentation of changes, and checks in that Rust project.
Why use it?
It gives an agent project-specific working rules so changes follow the repository's expectations rather than generic habits.

Instructions file for CodexOpenCode

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

This is srothgan/claude-code-rust's own configuration. It tells Codex and OpenCode how to work on claude-code-rust 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 claude-code-rust configures →

Reuse

Borrowing it

Nothing to install: this file belongs to srothgan/claude-code-rust. 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/srothgan/claude-code-rust/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/srothgan/claude-code-rust

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 claude-code-rust AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/srothgan/claude-code-rust/agents-md/github.svg)](https://agentmods.dev/instructions/srothgan/claude-code-rust/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/srothgan/claude-code-rust/agents-md"><img src="https://agentmods.dev/badge/instructions/srothgan/claude-code-rust/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 claude-code-rust AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/srothgan/claude-code-rust/agents-md"><img src="https://agentmods.dev/badge/instructions/srothgan/claude-code-rust/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,686 This file is loaded in full into every session.
When invoked 2,686 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 $0.02686 $0.02686
Opus 5.5 $0.01074 $0.01074
Sonnet 5.5 $0.00537 $0.00537
Haiku 4.5 $0.00269 $0.00269

Measured 9d ago against content hash 3baea868b325, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-rust 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 · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Working Style

  • Be precise, concise, and evidence-based. Avoid vague statements and unnecessary long explanations.
  • Inspect the relevant code, configuration, tests, and existing patterns before changing behavior.
  • For clear, scoped implementation requests, proceed without asking for another approval.
  • For open-ended feature or design requests with more than one viable approach, present the options and a recommendation before editing.
  • Ask for clarification only when ambiguity materially affects behavior, scope, data, security, or an irreversible/external action.
  • Verify assumptions that could affect correctness. When version- or API-specific behavior matters, prefer official documentation.
  • Keep changes focused on the requested work. Avoid unrelated refactors or cleanup.
  • Prefer established repository patterns unless there is a concrete reason to change them.

Discussing

Focus on substance over praise. Skip unnecessary compliments, engage critically with my ideas, question my assumptions, identify my biases, and offer counterpoints when relevant. Don't shy away from disagreement, and ensure that any agreements are grounded in reason and evidence.

Change Discipline

Complete the relevant change

Understand which parts of the system the requested behavior actually crosses and update all affected parts.

Depending on the task, this may include runtime behavior, domain logic, persistence, schemas, generated artifacts, external interfaces, tests, documentation, or obsolete code.

Do not treat this as a mechanical checklist. Update what is relevant to the real workflow and no more.

Follow the real workflow

Reason from the actual entry point through downstream behavior instead of modifying only the directly mentioned function or file.

Where relevant, consider:

  • success and empty cases;
  • partial and failure paths;
  • retry or reuse behavior;
  • boundary conditions;
  • persistence or serialization round-trips;
  • downstream consumers.

Read the full file on GitHub · 227 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 Changed · +8 tokens per session 3baea868b325
  2. 21d ago Changed · +1 lines · +48 tokens per session 506f892ff285
  3. 1mo ago Changed · +1 lines · +132 tokens per session c369a316e11c
  4. 1mo ago Changed · +1 lines · +48 tokens per session 552536b771a0
  5. 1mo ago First seen · 224 lines · 2,450 tokens per session scan A dada5a4c946e

Subscribe to this mod's changes

claude-code-rust AGENTS.md is an instructions file published in the GitHub repository srothgan/claude-code-rust (275 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,686 tokens to every session, about $0.0107 per session on Opus 5.5. 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 2026-10-02.

Related

claude-code-rust AGENTS.md compared with instructions from other repositories

claude-code-rust AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-code-rust AGENTS.mdsrothgan/claude-code-rustInstructions file2754d agoApache-2.0A2,686Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode