What is git-steer CLAUDE.md?

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.

Use them when changing git-steer’s TypeScript code, GitHub integration, repository-management features, security scanning, or development workflow.

They provide the project context needed to build, test, and maintain the tool without overlooking established decisions or conventions.

git-steer CLAUDE.md — Instructions file by ry-ops

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/ry-ops/git-steer/claude-md

Clone the repo

git clone --depth 1 https://github.com/ry-ops/git-steer

Per session 226 This file is loaded in full into every session.

When invoked 226 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.

Model	Per session	Once invoked
Fable 5	$0.00226	$0.00226
Opus 5	$0.00113	$0.00113
Sonnet 5	$0.00045	$0.00045
Haiku 4.5	$0.00023	$0.00023

Measured yesterday against content hash d97714da1cd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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 · 32 lines

What it actually says

Git-Steer Project

Git-Steer is an MCP server for GitHub repository management. It provides tools for repo settings, branch management, PR workflows, and security scanning.

Project Structure

src/mcp/server.ts - MCP server with all tool definitions
src/github/client.ts - GitHub API client
src/core/ - Core functionality (keychain, setup, etc.)
bin/cli.js - CLI entry point

Development

npm run build    # Compile TypeScript
npm run dev      # Development mode
npm test         # Run tests

Aiana Integration

Aiana is available as an MCP server for conversation memory. Use her proactively:

memory_recall - Get context about git-steer from past sessions
memory_search - Search past conversations for relevant info
memory_add - Save important decisions or patterns

When working on git-steer, check Aiana for:

Previous discussions about architecture decisions
Patterns established in past sessions
User preferences for this project

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.

yesterday 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 4d ago), licensed MIT. It adds 226 tokens to every session, about $0.0011 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 2026-08-31.

Git and workflow Memory and context Security automation github github-actions mcp mcp-server

copilot-instructions-project-structure copilot-instructions.md

Copilot instructions for jlantz/copilot-instructions-project-structure, covering copilot instructions for project structure workflow, package (js): , package (js): sample-js-project, package (js): sample-ts-project and package (py): sample-python-project.

jlantz/copilot-instructions-project-structure · 856 tokens

github-mcp-server copilot-instructions.md

Copilot instructions for github/github-mcp-server, covering github mcp server - copilot instructions, project overview, critical build & validation steps, required commands (run before committing) and when modifying mcp tools/endpoints.

github/github-mcp-server · 3,217 tokens

av CLAUDE.md

Instructions for aviator-co/av, covering claude.md, project overview, documentation sources, command structure philosophy and development workflow.

aviator-co/av · 1,531 tokens

vscode-gitlens CLAUDE.md

Claude Code instructions for gitkraken/vscode-gitlens, a project described as: Supercharge Git inside VS Code and unlock untapped knowledge within each repository — Visualize code authorship at a glance via Git blame annotations and CodeLens, seamlessly navigate and explore Git repositories, gain valuable insights via…

gitkraken/vscode-gitlens · 5 tokens

ghtkn AGENTS.md

Instructions for suzuki-shunsuke/ghtkn, a project described as: A CLI to create short-lived (8 hours) GitHub App User Access Token for secure local development.

suzuki-shunsuke/ghtkn · 14 tokens

ConsultMe CLAUDE.md

Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.

Tarek-Bohdima/ConsultMe · 3,021 tokens