Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/klboke/kkrepo/protocol-compatgit clone --depth 1 https://github.com/klboke/kkRepoWrote 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/klboke/kkrepo/protocol-compat)<a href="https://agentmods.dev/instructions/klboke/kkrepo/protocol-compat"><img src="https://agentmods.dev/badge/instructions/klboke/kkrepo/protocol-compat.svg" alt="Measured on agentmods" 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 | $0.00191 | $0.00191 |
| Opus 5 | $0.00096 | $0.00096 |
| Sonnet 5 | $0.00038 | $0.00038 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
kkRepo protocol-compat.instructions.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 4d 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
Protocol Compatibility Instructions
- Check the official protocol and Nexus behavior before changing hosted, proxy, or group repository behavior.
- Keep URL layout compatible with
/repository/<repo>/...unless a protocol-specific endpoint requires another layout. - For hosted writes, preserve write policy, checksum, metadata, and error response semantics.
- For proxy repositories, treat upstream status, headers, cache TTLs, negative cache, conditional requests, and body-read failures carefully.
- For group repositories, preserve member ordering and deterministic conflict handling.
- Add or update black-box compatibility tests under
compat-testwhen protocol behavior changes. - Do not mark protocol work complete until real client behavior or compatibility tests cover the changed path.
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.
- 4d ago First seen · 14 lines · 191 tokens per session scan A bc8dc70ceb07
kkRepo protocol-compat.instructions.md is an instructions file published in the GitHub repository klboke/kkRepo (258 stars, last pushed 4d ago), licensed Apache-2.0. It adds 191 tokens to every session, about $0.0010 per session on Opus 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.
Other instructions, from other repositories
supply-chain-hardening AGENTS.md
Instructions for jlevy/supply-chain-hardening, covering agents.md, common intents, safety rule for agents, untrusted repos and repo-supplied agent config is untrusted input.
node-modules-inspector AGENTS.md
Instructions for antfu/node-modules-inspector, covering agents.md, layout, commands (from repo root) and conventions.
api2mcp4j CLAUDE.md
Claude Code instructions for TheEterna/api2mcp4j, covering claude.md, 项目概述, 顶层授权框架（必读）, 开发心法与规范导航 and 通用心法（docs/rules/global/，所有会话默认生效）.
pi-coding-agent-forge AGENTS.md
AGENTS.md instructions for Firstp1ck/pi-coding-agent-forge, covering repository documentation rules, documentation goal, required documentation layers, readme.md — human guide and technical.md — advanced user reference.
mail-time CLAUDE.md
Instructions for veliovgroup/mail-time, covering claude.md, what this repo is, where to look first, mental model for changes and common pitfalls to avoid.
deptrust AGENTS.md
Instructions for clidey/deptrust, covering what this is, commands, architecture, adding an ecosystem and distribution.