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.
npx agentmods add instructions/aviator-co/av/claude-mdgit clone --depth 1 https://github.com/aviator-co/avWrote 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.
[](https://agentmods.dev/instructions/aviator-co/av/claude-md)<a href="https://agentmods.dev/instructions/aviator-co/av/claude-md"><img src="https://agentmods.dev/badge/instructions/aviator-co/av/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01531 | $0.01531 |
| Opus 5 | $0.00766 | $0.00766 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
av 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
av is a command-line tool for managing stacked PRs on GitHub. It allows developers to create dependent pull requests and automatically manages rebasing when base PRs are updated.
Documentation Sources
This project maintains documentation in three equally important locations:
- README.md: Repository overview, quick start guide, and installation instructions in the root directory
- https://docs.aviator.co/aviator-cli: Comprehensive online documentation covering all features and workflows
- Man pages: Detailed command reference documentation in markdown format within the
docs/directory, converted to man page format
Command Structure Philosophy
The CLI follows a flat command structure where commands are added as root-level commands rather than nested subcommands:
- Preferred: Root commands with flags (e.g.,
av commit,av restack) - Historical: The project has migrated away from layered commands (e.g.,
av stack commit→av commit) - Guidance for new commands: Add new functionality as root commands in
cmd/av/, not as subcommands
Some legacy subcommands remain (e.g., av stack foreach, av pr status) but new features should follow the flat structure.
Development Workflow
After making code changes, always run the following checks and fix any issues before committing:
- Build:
go build ./... - Lint:
go tool golangci-lint run - Test (if relevant):
go test -v --vet=all ./...or the specific package you changed
Build and Development Commands
Running the CLI
go run ./cmd/av [subcommand/flags...]
Building
go build -v ./...
Testing
# Run all tests with verbose output and vet checks
go test -v --vet=all ./...
# Run specific test packages
go test ./internal/git/...
go test ./e2e_tests/...
Linting
The project uses golangci-lint for code quality checks (pinned via tool directive in go.mod):
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.
- 5d ago First seen · 149 lines · 1,531 tokens per session scan A 2bb4eb7dd39d
av CLAUDE.md is an instructions file published in the GitHub repository aviator-co/av (511 stars, last pushed 4d ago), licensed MIT. It adds 1,531 tokens to every session, about $0.0077 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.
Other instructions, from other repositories
claude-codex-settings CLAUDE.md
Claude Code instructions for fcakyon/claude-codex-settings, covering claude-settings, repo structure, cross-tool plugin format reference, plugin manifests and root marketplace files.
claude-codex-settings AGENTS.md
AGENTS.md instructions for fcakyon/claude-codex-settings, a project described as: Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
claude-codex-settings GEMINI.md
Gemini CLI instructions for fcakyon/claude-codex-settings, a project described as: Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
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.
ghtkn AGENTS.md
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.
dev_agent
Expert engineer for this GitHub Action.