Borrowing it
Nothing to install: this file belongs to thangnq111203/oss-steward. 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/thangnq111203/oss-steward/main/AGENTS.mdgit clone --depth 1 https://github.com/thangnq111203/oss-stewardWrote 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/thangnq111203/oss-steward/agents-md)<a href="https://agentmods.dev/instructions/thangnq111203/oss-steward/agents-md"><img src="https://agentmods.dev/badge/instructions/thangnq111203/oss-steward/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/thangnq111203/oss-steward/agents-md"><img src="https://agentmods.dev/badge/instructions/thangnq111203/oss-steward/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 | $0.00265 | $0.00265 |
| Opus 5.5 | $0.00106 | $0.00106 |
| Sonnet 5.5 | $0.00053 | $0.00053 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
oss-steward AGENTS.md scanned grade A with 1 finding 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 2mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Do not use `eval`, `new Function`, or interpolated `child_process` calls. What it actually says
Agent instructions for oss-steward
These rules are loaded by the pull-request review workflow. Coding agents and human reviewers should follow them.
Rules
- Do not commit secrets, API keys, tokens, or private key material.
- Prefer parameterized queries; do not concatenate untrusted input into SQL.
- Do not use
eval,new Function, or interpolatedchild_processcalls. - Do not disable TLS verification (
rejectUnauthorized: false). - Every change under
src/should include or update a test undertests/. - Keep workflow logic pure: no network calls inside
src/workflows/. - Fail closed on invalid model JSON; never auto-approve when parsing fails.
- Do not scan third-party repositories the applicant does not own.
- Record usage and adoption limits honestly in the readiness report. Do not invent stars, downloads, or OpenAI selection.
- Treat model output as untrusted input. Validate it against a schema before merge. Never let the model drive a shell command.
Review focus
- Correctness of maintainer workflow outputs (findings, labels, version notes).
- Offline path remains complete when
OPENAI_API_KEYis absent. - Criteria alignment scores real files and real function outputs.
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.
- 2mo ago First seen · 26 lines · 265 tokens per session scan A 4cd58162afa1
oss-steward AGENTS.md is an instructions file published in the GitHub repository thangnq111203/oss-steward (87 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 265 tokens to every session, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
oss-steward AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oss-steward AGENTS.mdthangnq111203/oss-steward | Instructions file | 87 | 2mo ago | Apache-2.0 | A | 265 | 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 |