Borrowing it
Nothing to install: this file belongs to xkumakichi/xaip-protocol. 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/xkumakichi/xaip-protocol/main/AGENTS.mdgit clone --depth 1 https://github.com/xkumakichi/xaip-protocolWrote 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/xkumakichi/xaip-protocol/agents-md)<a href="https://agentmods.dev/instructions/xkumakichi/xaip-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/xkumakichi/xaip-protocol/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/xkumakichi/xaip-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/xkumakichi/xaip-protocol/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 | $0.00746 | $0.00746 |
| Opus 5.5 | $0.00298 | $0.00298 |
| Sonnet 5.5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
xaip-protocol 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI-Assisted Contribution Guide
This file is for AI assistants and maintainers who work on this repository. It defines the public wording boundaries, commit conventions, privacy rules, and verification steps that apply to any change submitted, regardless of which assistant or human authored it.
1. Public wording boundaries
These constraints apply to everything that lands in the public tree (README, docs/, source comments, error messages, package descriptions, PR descriptions, release notes):
- XAIP is not a sandbox.
- XAIP is not an approval engine.
- XAIP is not a payment rail.
- XAIP does not make tools safe.
- XAIP does not guarantee trust.
- Receipts are the primary artifact; scores and eligibility are derived views.
- The Internet-Draft is an individual Internet-Draft. Do not call it an IETF standard, an IETF-approved protocol, or a standardized protocol. It has no formal standing in the IETF standards process.
Avoid these phrasings in any public text:
best tool, safe tool, trusted tool, guaranteed, verified by, approved, recommended, the standard, right tool / server / skill, payment rail (except in negation).
2. Commit and PR rules
- Do not add AI-vendor
Co-Authored-Bytrailers to commit messages. Some AI assistants (for example, Claude Code) append these by default; they should be removed before committing. - Do not add "Generated with Claude Code" or any similar AI-vendor footer to PR descriptions.
- Keep commit messages neutral and scoped. One commit = one logical change.
- Privacy-related commit messages must not contain leaked values, personal names, third-party names, or email addresses. Use neutral framing (example:
chore(privacy): remove local agent config from public tree).
3. Privacy rules
- Do not put personal names, private email addresses, local configuration, credentials, or private strategy notes in any file that lands in the public tree.
- Local agent configuration files (per-assistant memory, per-IDE settings) must remain untracked. Add them to
.gitignorerather than committing them. - Do not embed API keys, tokens, or absolute local paths in committed files.
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 · 58 lines · 746 tokens per session scan A 1e527c787d50
xaip-protocol AGENTS.md is an instructions file published in the GitHub repository xkumakichi/xaip-protocol (2 stars, last pushed 3mo ago), licensed MIT. It adds 746 tokens to every session, about $0.0030 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.
xaip-protocol AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xaip-protocol AGENTS.mdxkumakichi/xaip-protocol | Instructions file | 2 | 3mo ago | MIT | A | 746 | 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 | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| 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 |