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/kcsinclair/kaos-control/gemini-mdgit clone --depth 1 https://github.com/kcsinclair/kaos-controlWrote 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/kcsinclair/kaos-control/gemini-md)<a href="https://agentmods.dev/instructions/kcsinclair/kaos-control/gemini-md"><img src="https://agentmods.dev/badge/instructions/kcsinclair/kaos-control/gemini-md.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 | $0.00005 | $0.00005 |
| Opus 5 | $0.00003 | $0.00003 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00001 | $0.00001 |
Grade A, and why
kaos-control GEMINI.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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 2 lines · 5 tokens per session scan A 336cc4fbf19b
kaos-control GEMINI.md is an instructions file published in the GitHub repository kcsinclair/kaos-control (15 stars, last pushed 8d ago), with no licence file. It adds 5 tokens to every session, about $0.0000 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
mantis AGENTS.md
AGENTS.md instructions for google/mantis, covering agent rules, before committing, verbatim blocks, reference files and extraction criteria.
repowire CLAUDE.md
Claude Code instructions for prassanna-ravishankar/repowire, covering claude.md, philosophies, long-running session notes, build, test, release and architecture.
cc-use-exp copilot-instructions.md
Copilot instructions for doccker/cc-use-exp, covering github copilot 仓库级指令, ai 协作三原则, 工作方式, 质量要求 and 协作与输出.
cc-use-exp api-design-safety.instructions.md
Instructions for doccker/cc-use-exp, covering api 设计安全规范, 6 个核心陷阱速记, 响应字段语义, 异常类型对照 and 下游产物必填字段三层次（生成前一次画全）.
cc-use-exp async-task-pattern.instructions.md
Instructions for doccker/cc-use-exp, covering 异步任务模式规范, 触发条件, 5 个核心陷阱速记, 必检清单 and 反模式.
cc-use-exp code-quality.instructions.md
Instructions for doccker/cc-use-exp, covering 模块化设计六原则, 1. 模块大小适中, 2. 减少调用深度, 3. 多扇入，少扇出 and 4. 接口边界清晰 + 统一错误返回.