agentmods.dev

git-steer: Instructions file for Claude Code

CLAUDE.md

git-steer CLAUDE.md is an instructions file for Claude Code from ry-ops/git-steer. It costs 821 tokens per session, scanned A, original, MIT.

Project instructions for git-steer, a local tool that manages GitHub repositories. They describe its code structure, development commands, repository workflows, and use of Aiana for recalling project decisions.

In plain words
What is it for?
Use them when changing git-steer’s TypeScript code, GitHub integration, repository-management features, security scanning, or development workflow.
Why use it?
They provide the project context needed to build, test, and maintain the tool without overlooking established decisions or conventions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is ry-ops/git-steer's own configuration. It tells Claude Code how to work on git-steer 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 git-steer configures →

not rated 1repo changed 18d ago A scan 821 tokens original MIT
View source ↗ ry-ops/git-steer
Reuse

Borrowing it

Nothing to install: this file belongs to ry-ops/git-steer. 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/ry-ops/git-steer/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ry-ops/git-steer

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 git-steer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ry-ops/git-steer/claude-md/github.svg)](https://agentmods.dev/instructions/ry-ops/git-steer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ry-ops/git-steer/claude-md"><img src="https://agentmods.dev/badge/instructions/ry-ops/git-steer/claude-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 git-steer CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ry-ops/git-steer/claude-md"><img src="https://agentmods.dev/badge/instructions/ry-ops/git-steer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 821 This file is loaded in full into every session.
When invoked 821 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 $0.00821 $0.00821
Opus 5.5 $0.00328 $0.00328
Sonnet 5.5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 18d ago against content hash 2db1d0fa40f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-steer CLAUDE.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 18d 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.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git-Steer Project

Git-Steer looks after a fleet of GitHub repositories and runs only on GitHub and other services such as Cloudflare (ADR-008 C-008-001, adr/ADR-008.yaml; the move to Cloudflare is planned in stages in ROADMAP.md, starting with the clock): GitHub-native protection, self-healing repos, and a read-only fleet view. It is never run on a workstation, and nothing in it writes to more than one repo per run.

Project Structure

  • adr/ - Architecture decisions; ADR-008 is current
  • src/github/client.ts - Rate-limit-hardened GitHub API client (throttle/retry, ETag cache, concurrency caps)
  • src/state/manager.ts - Reads/writes the git-steer-state repo
  • src/fleet/ - Fleet report (ADR-009 Layer 2): collect.ts reads the fleet through the read-only reporter App, render.ts builds the dashboard issue from status.json, scan.ts renders a single-repo scan, fix.ts builds a Fix plan for one repo, fleetfix.ts for an owner or the fleet, handoff.ts writes Hand-off issues, CI first (ADR-011)
  • src/rollout/ - Rollouts (ADR-010, ADR-011): change types in changes/ (check + apply; targets are repos, orgs or pull requests), the rollout issue format, the hourly plan, check/apply/check per target
  • src/dashboard/ - Old dashboard HTML, used by scripts/ci-dashboard.mjs (retired design)
  • scripts/ - rollout-{start,plan,apply,record}.mjs (run by the rollout workflows in git-steer-fleet), fleet-report.mjs (runs src/fleet from the private git-steer-fleet repo), repo-scan.mjs (read-only scan of one repo, asked for with a "scan owner/repo" issue in git-steer-fleet), fix-plan.mjs (Fix: plan plus a merge rollout, from a "fix owner/repo", "fix " or "fix fleet" issue), handoff-{plan,open,reply}.mjs (Hand off to Copilot, from a "handoff owner/repo", "handoff ci " or "handoff ci fleet" issue), app-audit.mjs (App permissions audit; runs only from the private git-steer-fleet repo), ci-dashboard.mjs (Layer 2 building block), ci-changelog.mjs
  • .github/workflows/ - ci.yml, lockfiles.yml (Layer 1 prototype), others

Read the full file on GitHub · 43 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. 18d ago Changed · +38 tokens per session 2db1d0fa40f6
  2. 26d ago Changed · +181 tokens per session 81c71950357a
  3. 1mo ago Changed · +11 lines · +376 tokens per session a4ead3d0b597
  4. 2mo ago First seen · 32 lines · 226 tokens per session scan A d97714da1cd3

Subscribe to this mod's changes

git-steer CLAUDE.md is an instructions file published in the GitHub repository ry-ops/git-steer (1 stars, last pushed 18d ago), licensed MIT. It adds 821 tokens to every session, about $0.0033 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 2026-08-31.

DevOps and cloudGit and workflowMemory and contextautomationgithubgithub-actionsmcpmcp-server
Related

git-steer CLAUDE.md compared with instructions from other repositories

git-steer CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git-steer CLAUDE.mdry-ops/git-steerInstructions file118d agoMITA821Claude Code
repobrain copilot-instructions.mdstudy8677/repobrainInstructions file1.4k14d agoMITA229GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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