Borrowing it
Nothing to install: this file belongs to steerlabs/opensteer. 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/steerlabs/opensteer/main/AGENTS.mdgit clone --depth 1 https://github.com/steerlabs/opensteerWrote 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/steerlabs/opensteer/agents-md)<a href="https://agentmods.dev/instructions/steerlabs/opensteer/agents-md"><img src="https://agentmods.dev/badge/instructions/steerlabs/opensteer/agents-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.
<a href="https://agentmods.dev/instructions/steerlabs/opensteer/agents-md"><img src="https://agentmods.dev/badge/instructions/steerlabs/opensteer/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02085 | $0.02085 |
| Opus 5.5 | $0.00834 | $0.00834 |
| Sonnet 5.5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
opensteer 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 today.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Landing changes
Work in your own worktree on a small branch and open one PR per change on
steerlabs/opensteer with a
conventional title (fix:, feat:, docs:, refactor:, test:, chore:).
Before pushing, run pnpm check:changed --base origin/main and the focused
journey that proves the behavior. Include what changed, why, evidence and any
checks you could not run in the PR.
After pushing, use watch_pull_request. Fix failing checks on the branch; never
weaken a test to land. No batching or up-to-date requirement. Main runs the full
CI suite; fix forward or revert a red main immediately. Real desktop journeys run
after merge and on maintainer request. Release builders consume the green main SHA.
You may squash-merge your own PR once the required Check is green and Greptile,
the automated reviewer, has no unresolved P0 or P1 finding. PRs that touch
security, signing, release workflows or credentials wait for Tim Jang's approval.
Testing
- Test what a person would notice breaking, at the cheapest layer that can catch it. Use real collaborators where they're cheap. Add an end-to-end journey only when the bug only shows end to end: one journey per user-facing flow, not per edge case.
- Every test earns its place: it guards something specific, it's quick and it isn't a duplicate. Deleting duplicate, superseded or never-useful tests is maintenance. Never drop the only coverage of a past real bug or a security property without moving it somewhere cheaper.
- Fix bugs at the root, with a regression test that fails first. Before changing ownership, wire contracts or cross-process architecture, get one review of the smallest design, then build it.
- Never weaken assertions or timeouts to get green. Skipped is not passed. Fix failures at the root before landing (flaky tests).
- Anything that drives the real screen, keyboard, windows or Electron runs in a
disposable VM (
pnpm test:vm), never on the host screen. Pure-logic Swift runs on the host withswift test. The VM journeys run after merge or on demand, never as a pre-merge gate. Emulators and USB phones have one owner at a time. - Stop every process you start, including after failures: servers, emulators,
adbservers and capture loops. They take phones and screen capture away from everything else on this Mac. - If one blocker has eaten about 15 minutes, report the evidence, your hypothesis and your next step instead of grinding.
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.
- today First seen · 144 lines · 2,085 tokens per session scan A 0ef5f2749598
opensteer AGENTS.md is an instructions file published in the GitHub repository steerlabs/opensteer (204 stars, last pushed today), licensed MIT. It adds 2,085 tokens to every session, about $0.0083 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 2026-10-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.