outrider src-run.instructions.md

outrider src-run.instructions.md is an instructions file for GitHub Copilot from remyxai/outrider. It costs 285 tokens per session, scanned A, original, Apache-2.0.

Rules for safely editing a single large Python file, src/run.py, which contains the project's main logic.

In plain words
What is it for?
Use them when modifying src/run.py, adding behavior and tests, updating model rates, or changing the refinement sequence that runs checks and tests.
Why use it?
They reduce the risk of breaking shared state, skipping required tests, changing pricing data incorrectly, or disrupting the required processing order.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

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/remyxai/outrider/src-run
Clone the repo
git clone --depth 1 https://github.com/remyxai/outrider

Made for: GitHub Copilot.

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 src-run.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/remyxai/outrider/src-run.svg)](https://agentmods.dev/instructions/remyxai/outrider/src-run)
Your own site
<a href="https://agentmods.dev/instructions/remyxai/outrider/src-run"><img src="https://agentmods.dev/badge/instructions/remyxai/outrider/src-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 285 This file is loaded in full into every session.
When invoked 285 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 5.1 $0.00285 $0.00285
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 6d ago against content hash 3aec16d356d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

outrider src-run.instructions.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 6d 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.

.github/instructions/src-run.instructions.md · 14 lines

What it actually says

src/run.py conventions

  • Single-file by design. ~16K LOC. Do not split into modules — session-crossing state, single import point for the composite action.
  • Search before writing. Grep for def <name> or the concept — the function you want probably exists (_github_token, _record_claude_usage, run_fidelity_audit, _mint_bot_token).
  • Test before commit. Every new behavior needs a test in tests/test_<area>.py. Existing tests use monkeypatch to intercept subprocess, gh_api, and Claude CLI calls.
  • No new error handling for scenarios that can't happen. Trust framework guarantees inside outrider. Only validate at external boundaries — GitHub API responses, action inputs, Claude subprocess output.
  • Don't touch _BACKEND_RATES structure. Additive rate-row updates only. Adding a model = new row + a matching test in test_model_base_url.py.
  • Chain-phase sequencing lives in run_refinement_chain (around L16410). fidelity → convention → test. fidelity_skipped_* continues to convention + test (except no_pr); fidelity_failed_* short-circuits.
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. 6d ago First seen · 14 lines · 285 tokens per session scan A 3aec16d356d0

Subscribe to this mod's changes

outrider src-run.instructions.md is an instructions file published in the GitHub repository remyxai/outrider (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 285 tokens to every session, about $0.0014 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.