Borrowing it
Nothing to install: this file belongs to rexleimo/aios. 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/rexleimo/aios/main/AGENTS.mdgit clone --depth 1 https://github.com/rexleimo/aiosWrote 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/rexleimo/aios/agents-md)<a href="https://agentmods.dev/instructions/rexleimo/aios/agents-md"><img src="https://agentmods.dev/badge/instructions/rexleimo/aios/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/rexleimo/aios/agents-md"><img src="https://agentmods.dev/badge/instructions/rexleimo/aios/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 | $0.07073 | $0.07073 |
| Opus 5.5 | $0.02829 | $0.02829 |
| Sonnet 5.5 | $0.01415 | $0.01415 |
| Haiku 4.5 | $0.00707 | $0.00707 |
Grade E, and why
aios AGENTS.md scanned grade E 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- RTK: `brew install rtk` or `curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh` (see https://github.com/rtk-ai/rtk#installation) Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **暂存目录必须与仓库同卷，并且真删时要落在安全门允许的路径里**（实测 2026-10-26，见 `docs/adr/0003-repo-junk-cleanup-tiering.md`）：`aios-tmp-gc.mjs` 的 `to-trash` 用 `fs.renameSync`，而 `trashDirFor()` 默认落 `os.homedir()/.Trash`——家目录与仓库不同卷时必须显式传 `--trash-dir Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- RTK: `brew install rtk` or `curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh` (see https://github.com/rtk-ai/rtk#installation) How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Path Conventions (路径约定)
IMPORTANT: All relative paths in this document are relative to the PROJECT ROOT (current working directory), NOT AIOS_ROOT.
AIOS_ROOT- AIOS framework installation location (containsscripts/,package.json)- Project Root - Current working directory (contains
.aios/,.codex/skills/, project state) - Paths like
.aios/,.codex/skills/,docs/plans/are relative to Project Root - Run
pwdto see Project Root;echo $AIOS_ROOTto see framework location - See
docs/architecture/path-resolution.mdfor detailed path resolution rules
Evaluate the AIOS workflow policy before creating a plan, selecting a skill, or dispatching work.
directandnoopturns do not create a persistent plan or invoke a skill chain.guardedturns use only the required edit and verification gates.plannedturns create or reuse one work-item plan, then execute only the Provider selected by the current rex Command.- Do not insert a global bootstrap or compatibility skill chain.
aios-workflow-routerhelps classify work but does not replace the Provider selected by the current Rex Capability Command. - Invoke the selected Provider rather than paraphrasing it; use
verification-before-completionbefore claiming a changed behavior is complete. - Code-producing Providers (
rex-implement/rex-design/rex-code-review/rex-refactor-hardening) load therex-engineering-standardsshared reference skill before executing; its Definition of Done (including file-granularity rules: one responsibility per file, ~400-line soft budget, kebab-case naming) gates completion.
Prompt Authoring Norms（提示词撰写规范）
Any prompt, skill, or script that guides the model follows three rules (full text: docs/reference/prompt-authoring-norms.md):
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 · +2 lines · +282 tokens per session scan C → E 49aafbbf1934
- 4d ago Changed · +38 lines · +922 tokens per session 341d3514dc38
- 5d ago Changed · +8 lines · +334 tokens per session 1ab0d2fb2c13
- 9d ago Changed · +8 lines · +297 tokens per session b40c2e379a8d
- 10d ago Changed · -38 lines · -343 tokens per session d09cbe152f46
- 13d ago Changed · +1 lines · +53 tokens per session 36567d87984a
- 28d ago Changed · +1 lines · +76 tokens per session 901f55a0e046
- 1mo ago Changed · +17 lines · +387 tokens per session 31109dd26986
- 1mo ago Changed · +1 lines · +135 tokens per session cf9502208a37
- 1mo ago First seen · 337 lines · 4,930 tokens per session scan C 084e0ecc2f36
aios AGENTS.md is an instructions file published in the GitHub repository rexleimo/aios (61 stars, last pushed today), licensed MIT. It adds 7,073 tokens to every session, about $0.0283 per session on Opus 5.5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.