Borrowing it
Nothing to install: this file belongs to Horace-Maxwell/horosa-skill. 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/Horace-Maxwell/horosa-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/Horace-Maxwell/horosa-skillWrote 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/horace-maxwell/horosa-skill/agents-md)<a href="https://agentmods.dev/instructions/horace-maxwell/horosa-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/horace-maxwell/horosa-skill/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/horace-maxwell/horosa-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/horace-maxwell/horosa-skill/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 | $0.59692 | $0.59692 |
| Opus 5.5 | $0.23877 | $0.23877 |
| Sonnet 5.5 | $0.11938 | $0.11938 |
| Haiku 4.5 | $0.05969 | $0.05969 |
Grade B, and why
horosa-skill AGENTS.md scanned grade B with 3 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Codex 里 horosa 一堆报错 / 首轮看不到工具 | 多半是 `startup_timeout_sec`/`tool_timeout_sec` 没写（Codex 默认 10 s/60 s，冷启动与择日扫描都超） | `horosa-skill client check --client codex`（v0.38.0 起缺省也报 `codex_*_timeout_missing`）；重跑 `client config --f Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`download()` 用 `curl`（Win10/11 自带）。 Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **子进程文本一律显式解码（v0.38.1 A1/A19）。** `subprocess.run(..., text=True)` 必带 `encoding=`（UTF-8，或 tasklist 的 `oem`） The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- today Changed · +4 lines · +200 tokens per session dfc5b1a12519
- yesterday Changed · +7 lines · +372 tokens per session c5c521ace37a
- 3d ago Changed · +30 lines · +1,442 tokens per session ff150dded3f2
- 4d ago Changed · +76 lines · +3,425 tokens per session 839da6736eee
- 6d ago Changed · +11 lines · +459 tokens per session 6b12a3bda893
- 7d ago Changed · +59 lines · +2,040 tokens per session f0d06494f31a
- 15d ago Changed · +35 lines · +1,736 tokens per session 59f136a06408
- 21d ago Changed · +6 lines · +356 tokens per session 5f448da5810c
- 26d ago Changed · +47 lines · +2,966 tokens per session 601fb58e5488
- 27d ago First seen · 1,199 lines · 46,696 tokens per session scan B 3ccc6996e702
horosa-skill AGENTS.md is an instructions file published in the GitHub repository Horace-Maxwell/horosa-skill (480 stars, last pushed yesterday), licensed AGPL-3.0. It adds 59,692 tokens to every session, about $0.2388 per session on Opus 5.5. A static security scan graded it B with 3 findings (reads agent configuration directories, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.