outrider: Skill for Claude Code

.claude/skills/outrider-experimentation/SKILL.md

outrider-experimentation is a skill for Claude Code from remyxai/outrider. It costs 130 tokens per session (2,547 once invoked), scanned A, original, Apache-2.0.

A guide for running and troubleshooting Outrider Action jobs, which are automated paper-to-code experiments carried out on software repositories.

In plain words
What is it for?
Use it to set up Outrider, start test or refinement runs, diagnose their results, and decide whether a generated change is ready to submit upstream.
Why use it?
It brings the setup commands, run logs, result summaries, and GitHub coordination checks into one workflow instead of requiring separate investigation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is remyxai/outrider's own configuration. It tells Claude Code 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/.claude/skills/outrider-experimentation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/remyxai/outrider

Made for: Claude Code.

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-experimentation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/remyxai/outrider/outrider-experimentation"><img src="https://agentmods.dev/badge/skills/remyxai/outrider/outrider-experimentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,547 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00130 $0.02547
Opus 5 $0.00065 $0.01273
Sonnet 5 $0.00026 $0.00509
Haiku 4.5 $0.00013 $0.00255

Measured 12d ago against content hash 2d60bbfb8329, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

outrider-experimentation 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 12d 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.

.claude/skills/outrider-experimentation/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outrider experimentation — field guide

Ambient knowledge for using Outrider effectively on target repos: from dispatch to upstream. All commands here are ones I've actually used in practice; nothing speculative.

When to use

  • Setting up Outrider on a new target repo
  • Dispatching a manual refinement / smoke run
  • Diagnosing why a run downgraded to Issue or opened at a different outcome than expected
  • Deciding whether an Outrider-drafted PR is ready to file upstream
  • Cross-checking a paper against existing coordination signals on the target repo

Set up Outrider on a target repo

Fastest path — CLI-generated workflow with the right backend selected:

remyxai outrider setup-local --repo owner/name --backend moonshot

Backends: anthropic (default, Opus), zai (GLM), moonshot (Kimi K3). Setup-local prompts only for the selected backend's secret; add others manually via gh secret set ANTHROPIC_API_KEY --repo owner/name < token.txt for per-dispatch switching.

Manual install (when the CLI shape doesn't quite fit): copy the workflow YAML from remyxai/outrider's .github/workflows/outrider.yml and thread the interest-id you get from remyxai interests get -f json.

Trigger manually

# Fresh recommend (let selection pass pick)
gh workflow run outrider.yml --repo owner/name --ref main

# Pin to a specific paper (skip selection)
gh workflow run outrider.yml --repo owner/name --ref main \
  -f pin-arxiv=2509.09675v1 \
  -f provider=moonshot \
  -f model=kimi-k3

# Refinement on an existing drafter branch
gh workflow run outrider.yml --repo owner/name --ref main \
  -f pin-arxiv=<id> \
  -f start-from-ref=<drafter-branch> \
  -f staged-synthesis=true \
  -f lead-content="REFINEMENT PASS on existing branch..."

# Convention pass on an already-open PR
gh workflow run outrider-convention.yml --repo owner/name --ref main -f pr-number=18

Key inputs to remember:

  • pin-arxiv: exact <id>[v<N>] — bypasses selection, best for reproducible runs
  • pin-method: free-text query for the selection pass to search (often prefer search-method; pin-method is a docs-only alias that GHA warns about)
  • start-from-ref: refinement mode — pins to an existing branch
  • staged-synthesis=true: enables research phase before coding (adds ~10 min for slow backends)
  • claude-timeout: bump to 3600 for Kimi K3 or GLM-5.2 (thinking-mode adds per-turn latency)
  • rate-limit-days=0: bypass the 7-day cadence guard for one-off smokes

Read the full file on GitHub · 182 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. 12d ago First seen · 182 lines · 130 tokens per session scan A 2d60bbfb8329

Subscribe to this mod's changes

outrider-experimentation is a skill published in the GitHub repository remyxai/outrider (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 130 tokens to every session and 2,547 once invoked, about $0.0006 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 skills, from other repositories

academic-research

Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…

Lingtai-AI/lingtai · 180 tokens

arxiv-mcp-server

Use when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or literature reviews.

blazickjp/arxiv-mcp-server · 43 tokens

scientific-writing

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…

LeonChaoX/qinyan-academic-skills · 87 tokens

venue-templates

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing…

LeonChaoX/qinyan-academic-skills · 97 tokens

iso-24495-3

Sector-specific Plain Language standard for science and technical writing (ISO 24495-3:2026). Applied during software documentation, architecture specs, and technical analysis.

GaZmagik/iso-24495 · 40 tokens

cbioportal-database

Query cBioPortal for cancer genomics data including somatic mutations, copy number alterations, gene expression, and survival data across hundreds of cancer studies. Essential for cancer target validation, oncogene/tumor suppressor analysis, and patient-level genomic profiling.

LeonChaoX/qinyan-academic-skills · 57 tokens