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/iofficeai/aionrs/agents-mdgit clone --depth 1 https://github.com/iOfficeAI/aionrsWrote 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/iofficeai/aionrs/agents-md)<a href="https://agentmods.dev/instructions/iofficeai/aionrs/agents-md"><img src="https://agentmods.dev/badge/instructions/iofficeai/aionrs/agents-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 | $0.02560 | $0.02560 |
| Opus 5 | $0.01280 | $0.01280 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade B, and why
aionrs AGENTS.md scanned grade B with 1 finding 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 5d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- `cargo clippy` must pass without warnings How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Rules and conventions for AI assistants and contributors working on aionrs.
Overview
aionrs is a multi-provider AI agent CLI written in Rust. It connects to LLM providers (Anthropic, OpenAI, AWS Bedrock, Google Vertex AI), orchestrates built-in tools (Read, Write, Edit, ExecCommand, Grep, Glob, ViewImage, Spawn), supports MCP servers, skills, hooks, and long-term memory. It also exposes a JSON stream protocol for host integration (e.g. Electron-based AionUI).
Tech stack: Rust 2021 edition, stable toolchain, Cargo workspace under crates/.
Crate Map
Dependencies flow downward — never introduce circular or upward references.
| Layer | Crate | Responsibility |
|---|---|---|
| Bottom | aion-types |
Shared provider-neutral data types (LLM, message, tool) — zero internal deps |
| Bottom | aion-compact |
Context compression algorithms (folding, sanitization, tokenization) |
| Mid | aion-config |
Configuration, ProviderCompat, auth, hooks, logging (create_file_layer), cross-platform shell helpers |
| Mid | aion-protocol |
JSON stream protocol (events, commands, approval manager) for host integration |
| Mid | aion-providers |
LLM provider implementations (Anthropic, OpenAI, Bedrock, Vertex) |
| Mid | aion-tools |
Local tools (Read, Write, Edit, ExecCommand, Grep, Glob, ViewImage, ToolSearch) |
| Mid | aion-mcp |
MCP (Model Context Protocol) client |
| Mid | aion-skills |
Skills system (prompt snippets, hooks, permissions, shell expansion) |
| Mid | aion-memory |
Long-term cross-session memory (user prefs, feedback, project context) |
| Top | aion-agent |
Agent engine, session management, orchestration, and agent-level tools such as Spawn |
| Top | aion-cli |
CLI binary entry point |
When adding new functionality, place it in the lowest crate where it
semantically belongs. Don't create a new crate just for one shared function.
Run cargo metadata to verify dependency changes fit the graph.
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.
- 5d ago First seen · 231 lines · 2,560 tokens per session scan B 8e462d00f55b
aionrs AGENTS.md is an instructions file published in the GitHub repository iOfficeAI/aionrs (121 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,560 tokens to every session, about $0.0128 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.