Borrowing it
Nothing to install: this file belongs to grcorsair/corsair. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/grcorsair/corsair/main/AGENTS.mdgit clone --depth 1 https://github.com/grcorsair/corsairWrote 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/grcorsair/corsair/agents-md)<a href="https://agentmods.dev/instructions/grcorsair/corsair/agents-md"><img src="https://agentmods.dev/badge/instructions/grcorsair/corsair/agents-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 5.1 | $0.01401 | $0.01401 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
corsair 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 7d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Corsair
This file defines how agents should work in this repo. Keep it short, accurate, and actionable. If it conflicts with README, this file wins for agent behavior.
Quick Commands (Bun)
bun install
bun test
bun test tests/cli/
bun test tests/parley/
bun test tests/flagship/
bun test tests/ingestion/
bun test tests/sign/
bun test tests/mcp/
bun test tests/api/
bun test tests/functions/
bun test tests/distribution/
bun test packages/sdk/tests/
bun run typecheck
bun run validate:connectors
bun run lint:web
bun run build:web
bun run dev:web
bun run corsair.ts sign --file <path>
bun run corsair.ts verify --file <cpoe.jwt>
bun run corsair.ts diff --current <new> --previous <old>
bun run corsair.ts trust-txt generate --did did:web:acme.com
bun run corsair.ts trust-txt validate <domain>
bun run corsair.ts trust-txt discover <domain>
bun run corsair.ts keygen
Tech Stack
- Runtime: Bun (default for scripts/tests)
- Language: TypeScript (strict, ESM)
- Web: Next.js 16 + Tailwind CSS v4 + shadcn/ui (
apps/web/) - Crypto:
jose+ platform crypto (Ed25519 JWT-VC) - Database: Railway Postgres via
Bun.sql - Deployment: Railway (
railway.json)
TDD Workflow (Required)
- Write the test first in
tests/(mirrorssrc/structure) - Run the test and confirm it fails (red)
- Implement the minimum fix/feature
- Run the test and confirm it passes (green)
- Refactor if needed; keep tests green
- Run
bun testbefore declaring work complete
Testing Conventions
- Test files:
*.test.ts - Use
import { describe, test, expect } from "bun:test" - Prefer a targeted test file first, then the full suite
Commit Messages (Conventional Commits)
feat:new featurefix:bug fixdocs:documentation onlychore:tooling/maintenancerefactor:code change without behavior changetest:tests onlystyle:formatting/no logic change
Scope is optional, e.g. feat(web): add trust.txt generator page.
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.
- 7d ago First seen · 117 lines · 1,401 tokens per session scan A 7c10b373f050
corsair AGENTS.md is an instructions file published in the GitHub repository grcorsair/corsair (14 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,401 tokens to every session, about $0.0070 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.