Borrowing it
Nothing to install: this file belongs to initxy/ai-native. 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/initxy/ai-native/main/AGENTS.mdgit clone --depth 1 https://github.com/initxy/ai-nativeWrote 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/initxy/ai-native/agents-md)<a href="https://agentmods.dev/instructions/initxy/ai-native/agents-md"><img src="https://agentmods.dev/badge/instructions/initxy/ai-native/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/initxy/ai-native/agents-md"><img src="https://agentmods.dev/badge/instructions/initxy/ai-native/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 | $0.00330 | $0.00330 |
| Opus 5.5 | $0.00132 | $0.00132 |
| Sonnet 5.5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
ai-native 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 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.
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.
What it actually says
Communication
- Answer first: the first sentence is the conclusion, result, or recommendation — never a restatement of the question, a plan, or a helper phrase.
- Default short: a few sentences for a question, short bullets for lists. Expand only when asked — offer detail instead of volunteering it.
- Don't narrate what you're about to do, and don't summarize what you just did unless asked; report only what changes what the reader does next.
- No filler, no flattery, no hedging. When uncertain, state the assumption and the risk in one line.
Language
- Docs: English.
README.zh.mdmirrorsREADME.md— every README change lands in both. - Replies / conversation: match the user's language.
Context
- The product is prose: the skill (
SKILL.md) plus the spec and templates it reads (references/). There is no code to build or run. references/harness.mdis the source of truth for the rules;references/templates.mdinstantiates them for target repos;SKILL.mdis the procedure that applies them. When a rule changes, changeharness.mdfirst, then reconcile the other two.- Solo-maintained. This repo doesn't carry the harness it lays down — target-repo files exist only inside
references/templates.md. - One fact, one home: never state the same fact in two docs — link instead.
Check
./scripts/check.shbefore calling anything done: SKILL.md frontmatter well-formed, relative markdown links resolve. CI runs the same script.
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 · 23 lines · 330 tokens per session scan A d836f860b09b
ai-native AGENTS.md is an instructions file published in the GitHub repository initxy/ai-native (5 stars, last pushed 11d ago), licensed MIT. It adds 330 tokens to every session, about $0.0013 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 2026-08-31.
ai-native AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-native AGENTS.mdinitxy/ai-native | Instructions file | 5 | 11d ago | MIT | A | 330 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | 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 oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |