outrider: Instructions file for Codex

AGENTS.md

outrider AGENTS.md is an instructions file for Codex, OpenCode from remyxai/outrider. It costs 1,717 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Outrider, a GitHub Action that turns arXiv research papers into draft pull requests or issues for software repositories. arXiv is an online archive of research papers.

In plain words
What is it for?
Use them when changing Outrider, its GitHub Action inputs, paper-to-code workflow, provider routing, draft pull requests, or test suite.
Why use it?
They explain how the action recommends papers, drafts implementations, runs checks, and routes requests to different Claude-compatible providers.

Instructions file for CodexOpenCode

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

This is remyxai/outrider's own configuration. It tells Codex and OpenCode how to work on outrider 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 outrider configures →

Reuse

Borrowing it

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

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 outrider AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/remyxai/outrider/agents-md"><img src="https://agentmods.dev/badge/instructions/remyxai/outrider/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,717 This file is loaded in full into every session.
When invoked 1,717 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 $0.01717 $0.01717
Opus 5 $0.00859 $0.00859
Sonnet 5 $0.00343 $0.00343
Haiku 4.5 $0.00172 $0.00172

Measured 9d ago against content hash 9115e5d51d1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

outrider 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 · 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 — Outrider

Guidance for AI coding agents working on this repository. Read this before touching source.

What this project is

Outrider is a GitHub Action that turns arXiv papers into draft PRs on target repos. It:

  1. Queries the Remyx engine for a paper recommendation against a repo's ResearchInterest.
  2. Clones the target repo, drafts an implementation via Claude Code, runs pytest + self-review.
  3. Opens a draft PR (or Issue when preflight downgrades) attributed to remyx-ai[bot].
  4. Optionally runs an inline refinement chain: fidelity audit → convention pass → test gate.

The Action is backend-agnostic through Claude Code's Anthropic-Messages-compatible endpoints — Anthropic (default), z.ai/GLM, Moonshot/Kimi via the provider action input.

Build & test

  • Full test suite: python3 -m pytest tests/ -q (~15s, ~1050 tests + 1 skipped)
  • Targeted: python3 -m pytest tests/test_bot_token_default.py -x -q
  • Validate action.yml: python3 -c "import yaml; yaml.safe_load(open('action.yml'))"
  • No pip install -e .; the action installs its own deps in action.yml's composite steps.

Run tests before every commit. New behavior needs pinning tests before the PR opens.

Architecture at a glance

  • src/run.py — main logic (~16K LOC, one file, intentionally). Selection, preflight, coding invocation, chain phases, cost telemetry, bot-token minting — all in here. Search for def before adding a function; the piece you want probably exists.
  • action.yml — composite-action step definitions. Inputs threaded into run.py via INPUT_* env vars. Adding a new input means an action.yml entry + a reader in run.py.
  • tests/ — every phase has its own test_*.py file. Tests intercept subprocess calls, GitHub API calls, and Claude CLI calls with monkeypatch stubs.
  • docs/ — customer-facing docs. backends.md is the canonical vendor table. customization.md is the input-shape reference.

Backend routing (provider input)

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. 9d ago First seen · 88 lines · 1,717 tokens per session scan A 9115e5d51d1e

Subscribe to this mod's changes

outrider AGENTS.md is an instructions file published in the GitHub repository remyxai/outrider (20 stars, last pushed today), licensed Apache-2.0. It adds 1,717 tokens to every session, about $0.0086 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 2026-08-30.

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 · 3,737 tokens