Borrowing it
Nothing to install: this file belongs to moonbitlang/openseek. 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/moonbitlang/openseek/main/AGENTS.mdgit clone --depth 1 https://github.com/moonbitlang/openseekWrote 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/moonbitlang/openseek/agents-md)<a href="https://agentmods.dev/instructions/moonbitlang/openseek/agents-md"><img src="https://agentmods.dev/badge/instructions/moonbitlang/openseek/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/moonbitlang/openseek/agents-md"><img src="https://agentmods.dev/badge/instructions/moonbitlang/openseek/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 | $0.01179 | $0.01179 |
| Opus 5.5 | $0.00472 | $0.00472 |
| Sonnet 5.5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
openseek 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 16d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Agents.md Guide
This is a MoonBit project.
You can browse and install extra skills here: https://github.com/moonbitlang/skills
Task Scope
- Use the requested outcome and explicit exclusions to define the change scope. Apply these conventions to the code and contracts touched by that work. Include broader cleanup or behavior changes when they are part of the requested outcome.
- Tie new defensive behavior to an existing contract or an agreed product requirement. State the triggering input or user action and the expected result so the check has a concrete purpose and completion criterion.
Project Structure
-
MoonBit packages are organized per directory; each directory contains a
moon.pkgfile listing its dependencies. Each package has its files and blackbox test files (ending in_test.mbt) and whitebox test files (ending in_wbtest.mbt). -
In the toplevel directory, there is a
moon.modfile listing module metadata.moon.mod.jsonis the legacy manifest format.
Coding convention
-
MoonBit code is organized in block style, each block is separated by
///|, the order of each block is irrelevant. In some refactorings, you can process block by block independently. -
Try to keep deprecated blocks in file called
deprecated.mbtin each directory. -
When adding or changing an API, represent expected absence with
T?or a dedicated enum variant, including in JSON payloads. Carry operational failures through an error channel or a tagged error case, and handle each result according to the owning API's contract. Changing what absence means is a behavior change and follows the task scope.
Tooling
-
moon fmtis used to format your code properly. -
moon ideprovides project navigation helpers likepeek-def,outline, andfind-references. Usemoon ide --helpfor the available commands. -
moon infois used to update the generated interface of the package, each package has a generated interface file.mbti, it is a brief formal description of the package. Review.mbtidiffs for public signature changes; use behavior tests to check runtime effects.
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.
- 16d ago Changed · +18 lines · +330 tokens per session f39773d27f11
- 18d ago Changed · +5 lines · +60 tokens per session adc4e8bd3284
- 23d ago Changed · -88 tokens per session 499420d638c1
- 2mo ago First seen · 77 lines · 877 tokens per session scan A 2bca820520dd
openseek AGENTS.md is an instructions file published in the GitHub repository moonbitlang/openseek (106 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,179 tokens to every session, about $0.0047 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 2026-08-30.
openseek AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| openseek AGENTS.mdmoonbitlang/openseek | Instructions file | 106 | yesterday | Apache-2.0 | A | 1,179 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |