Borrowing it
Nothing to install: this file belongs to spuentesp/lain. 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/spuentesp/lain/main/AGENTS.mdgit clone --depth 1 https://github.com/spuentesp/lainWrote 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/spuentesp/lain/agents-md)<a href="https://agentmods.dev/instructions/spuentesp/lain/agents-md"><img src="https://agentmods.dev/badge/instructions/spuentesp/lain/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/spuentesp/lain/agents-md"><img src="https://agentmods.dev/badge/instructions/spuentesp/lain/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 | $0.01413 | $0.01413 |
| Opus 5.5 | $0.00565 | $0.00565 |
| Sonnet 5.5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
lain 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 9d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — for AI agents working in this Lain checkout
Standard instructions
Check skills before working a task and look for a useful one
memory cleanliness is important. review we didnt fill the ram or the ssd with garbage data we can regenerate
testing is critical. we alwaya assume someone didnt do the job thats why we test
Add always at the start of each message this "Answer:"
Branch policy
Two-branch model:
dev— integration. Default branch. PRs targetdev. CI: fast lane (Ubuntu tests, lint, npm-shim, schema-drift, health-badge, capability suite, mutation gate). ~5 min.main— release line. Receives changes only via reviewed PRs fromdev, and only when cutting a new release. CI: full hardened battery (all OSes, capability suite, coverage, release contracts). ~20 min.
Feature branches are cut from dev and merged back into dev. Never target main directly.
dev → main is release-only, not a routine merge:
- Zero-pending audit — publishing is the LAST step, not the first.
Before cutting the branch: nothing half-done may remain. Check, and
record the evidence:
- every item in the acceptance findings register is closed or explicitly scoped out of the release in writing (with why);
- no open issues from the acceptance program;
- no known test flakes left unfixed;
- no uncommitted WIP in any worktree;
- the acceptance suites,
demo.sh, and the full test battery are green on the exact tree to be released. If anything is open, either land it in this release or write the deferral down first. A release that ships with a list of "pendientes" is half-done work.
- Branch
release/v0.x.yoffdev. - Bump every release-metadata file (
Cargo.toml,Cargo.lock,server.json,npm-shim/package.json,Formula/lain.rb).scripts/check-release-version.py --tag v0.x.yvalidates. Leave the health-badge action'slain-versiondefault on the latest PUBLISHED release — bumping it pre-tag deadlocks the release gate (the badge 404s on the unpublished version andrelease.ymlrefuses to build a commit whose CI is red). - PR against
main(1 review + green agent-contract). - After merge:
git push origin v0.x.ytriggersrelease.yml. - Fast-forward dev:
git switch dev && git merge --ff-only main. - After the release assets are published: fill
Formula/lain.rb'ssha256values from the publishedSHA256SUMSfile, and bump the health-badge action'slain-versiondefault to the new version. The artifacts are not bit-reproducible, so pre-filling the formula produces one that fails verification (this is how v0.8.0 shipped broken); pre-bumping the badge default deadlocks the release gate.
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.
- 9d ago Changed · +6 lines · -23 tokens per session da6a611f36e7
- 15d ago Changed · +1 lines · +40 tokens per session d3057d626786
- 24d ago Changed · +13 lines · +170 tokens per session 681ef9844332
- 26d ago Changed · +10 lines · +170 tokens per session b8543b3b36d2
- 1mo ago Changed · +12 lines · +172 tokens per session d5b4834cfcac
- 1mo ago Changed · +24 lines · +113 tokens per session scan C → A a8e219aee223
- 2mo ago Changed · +8 lines · +82 tokens per session f3b742a67e36
- 2mo ago First seen · 51 lines · 689 tokens per session scan C 723573fdf9de
lain AGENTS.md is an instructions file published in the GitHub repository spuentesp/lain (9 stars, last pushed today), licensed MIT. It adds 1,413 tokens to every session, about $0.0057 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 2026-09-04.
lain AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lain AGENTS.mdspuentesp/lain | Instructions file | 9 | today | MIT | A | 1,413 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |