What is carabiner AGENTS.md?

Repository instructions for coding agents working on the Carabiner project. They describe the project context, preferred programming languages and tools, and current work.

Use them when adding features, fixing bugs, or reviewing TypeScript, Rust, React, and related project files.

They give an agent the project’s background and working conventions, reducing guesswork when changing code.

carabiner AGENTS.md — Instructions file for Codex and OpenCode by outfitter-dev: Repository instructions for coding agents working on the Ca

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/outfitter-dev/carabiner/agents-md

Clone the repo

git clone --depth 1 https://github.com/outfitter-dev/carabiner

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/outfitter-dev/carabiner/agents-md.svg)](https://agentmods.dev/instructions/outfitter-dev/carabiner/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/outfitter-dev/carabiner/agents-md"><img src="https://agentmods.dev/badge/instructions/outfitter-dev/carabiner/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,127 This file is loaded in full into every session.

When invoked 2,127 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	$0.02127	$0.02127
Opus 5	$0.01064	$0.01064
Sonnet 5	$0.00425	$0.00425
Haiku 4.5	$0.00213	$0.00213

Measured 4d ago against content hash 56985b229131, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

carabiner AGENTS.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 4d 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.

AGENTS.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Current Work:

Provider adapter rollout: .agents/notes/hook-adapter-architecture.md

Logger & fixture plan (unified logger, fixtures, docs, lefthook): .agents/notes/logger-and-tests-plan.md

About Matt

Name: Matt Galligan
- "Matt" for short
- @galligan on GitHub
Profile:
- Full-stack product builder who leverages (and depends on) AI agents
- Working on "Outfitter"
  - GitHub: https://github.com/outfitter-dev
  - NPM: https://www.npmjs.com/outfitter
- Relevant links:
  - Github: https://github.com/galligan
  - X/Twitter: https://x.com/mg

Technology Stack

I default to using TypeScript (via Bun) for most projects. Where speed is a priority, I'll use Rust. Simply put, use the best tool for the job.

TypeScript

Preference: Strongly typed (strict settings)
Runtime: Bun
Package Manager: Bun
Server: Hono preferred, Express, Fastify, etc.

Rust

Preference: Speed, performance, and safety
Runtime: Rust
Package Manager: Cargo
Server: Axum, Actix, etc.

Frontends

Framework: React + TanStack Router/TanStack Start or Next.js
CSS/Styling: Tailwind CSS 4
Components: shadcn/ui, components stored in packages/ui/components
- DRY, reusable, and accessible components

Database

Starting Projects: SQLite by default (use Bun.SQL if TypeScript)
Production: PostgreSQL (with Supabase or Neon) or Convex
Redis Alternative: Upstash when relevant

API Design

Preference Order: tRPC > REST > GraphQL
Requirements: OpenAPI + Swagger documentation
Priority: MCP server compatibility

Deployment

Primary: Cloudflare preferred, Vercel
Alternatives: Open to Fly.io

Testing

Frameworks: Vitest, Playwright
Priority: Compatibility with MCP servers for agent automation

Authentication

Primary: BetterAuth
Alternative: Clerk

CI/CD

Primary: GitHub Actions (complex actions with Cloudflare runners)
Alternative: Vercel/Cloudflare integrated CI when deploying there

Read the full file on GitHub · 233 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.

4d ago First seen · 233 lines · 2,127 tokens per session scan A 56985b229131

Subscribe to this mod's changes

carabiner AGENTS.md is an instructions file published in the GitHub repository outfitter-dev/carabiner (4 stars, last pushed 7mo ago), licensed MIT. It adds 2,127 tokens to every session, about $0.0106 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.

Type Safety claude-code claude-code-hooks tooling typescript-library

carabiner AGENTS.md