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/alchemiststudiosdotai/alchemy-rs/agents-mdgit clone --depth 1 https://github.com/alchemiststudiosDOTai/alchemy-rsWrote 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/alchemiststudiosdotai/alchemy-rs/agents-md)<a href="https://agentmods.dev/instructions/alchemiststudiosdotai/alchemy-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/alchemiststudiosdotai/alchemy-rs/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 | $0.01429 | $0.01429 |
| Opus 5 | $0.00714 | $0.00714 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
alchemy-rs AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
alchemy-llmis a Rust crate that exposes a unified LLM API with a streaming-first interface.- Implemented runtime paths today are OpenAI-compatible Completions, MiniMax Completions, and z.ai Completions; other provider identities exist in the type layer but still return not-implemented errors from
src/stream/mod.rs. - The public crate surface is re-exported from
src/lib.rs.
Where To Start
- Start with
README.mdfor current provider status, public examples, and developer commands. - Read
src/lib.rsto see the exported modules and top-level helpers. - Read
src/stream/mod.rsnext; it is the mainstream(...)/complete(...)dispatch layer. - Read
docs/README.md, thendocs/providers/architecture.mdfor the provider implementation contract. - There is no top-level
ARCHITECTURE.md; usedocs/providers/architecture.mdas the architecture source of truth.
Repository Map
Cargo.toml- crate metadata, dependencies, and published package settings.src/lib.rs- public module wiring and re-exports.src/models/- model helper constructors (featherless_model, MiniMax helpers, z.ai helpers).src/providers/- provider runtimes, auth/env lookup, and provider-specific request handling.src/providers/shared/- shared OpenAI-like HTTP, message serialization, and stream block helpers.src/stream/- top-level dispatch and stream collection helpers.src/types/- canonical API, content, message, event, model, and usage types.src/transform.rs- cross-provider conversation transformation and tool-call replay handling.src/utils/- think-tag parsing helpers.src/test_helpers/- shared test utilities for inline module tests.docs/- compact docs index plus provider architecture / Featherless notes.rules/- ast-grep config and boundary rules.scripts/harness.sh- full validation harness used by local hooks..cargo-husky/hooks/pre-commit- pre-commit gate, including large-file blocking and harness execution..env.example- canonical env var names for provider credentials.
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 · 99 lines · 1,429 tokens per session scan A 5f73300c2f4f
alchemy-rs AGENTS.md is an instructions file published in the GitHub repository alchemiststudiosDOTai/alchemy-rs (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,429 tokens to every session, about $0.0071 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 2026-08-31.
Other instructions, from other repositories
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
bifrost AGENTS.md
Instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由（先判定，后执行）.
ton-rs AGENTS.md
AGENTS.md instructions for ston-fi/ton-rs, covering ton-rs agent guide, repository, boundaries, public api and ton invariants.