What is maki AGENTS.md?

A set of coding guidelines for Maki, an AI coding agent written in Rust. It covers code style, error handling, dependencies, tests, performance, and project structure.

Use it when Maki works on Rust code, especially in projects with a shared Cargo workspace, unit tests, and established dependency and error-handling practices.

It gives the agent consistent rules for making changes that fit the project and are easier to maintain and test.

How tontinton/maki configures Codex and OpenCode

About the project

Maki is an AI coding agent with a terminal interface and Lua plugins inspired by Neovim. Developers use it to work with code while reducing context usage through code indexing, data-processing tools, and delegated subagents. The catalogue command and instruction extend or configure this agent.

tontinton/maki · 1,374 stars · on GitHub · maki.sh

Reuse

Borrowing it

Nothing to install: this file belongs to tontinton/maki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tontinton/maki/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tontinton/maki

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tontinton/maki/agents-md/github.svg)](https://agentmods.dev/instructions/tontinton/maki/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tontinton/maki/agents-md"><img src="https://agentmods.dev/badge/instructions/tontinton/maki/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tontinton/maki/agents-md"><img src="https://agentmods.dev/badge/instructions/tontinton/maki/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,101 This file is loaded in full into every session.

When invoked 1,101 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01101	$0.01101
Opus 5.5	$0.00440	$0.00440
Sonnet 5.5	$0.00220	$0.00220
Haiku 4.5	$0.00110	$0.00110

Measured 6d ago against content hash 1e44068bbfd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maki 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 6d 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.

AGENTS.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maki is an AI coding agent (like Claude Code and opencode), that is built bottom up to optimize costs and number of tokens used, while not sacrificing performance too much.

Code guidelines

No trivial comments
Minimal bloat (KISS, DRY, SRP)
No unnecessary state (variables, fields, arguments)
Each line of code should justify its existence
Follow Rust idioms and best practices
Latest Rust features can be used
Descriptive variable and function names
No wildcard imports
Import types at top of file and use short names everywhere (e.g. use std::sync::Arc; then Arc<T>, never std::sync::Arc<T> inline)
Keep consts at top of file, right after imports
Explicit error handling with Result<T, E> over panics
Use color_eyre when the specific error is not as important
Use custom error types using thiserror for domain-specific errors
Place unit tests in the same file using #[cfg(test)] modules
Add dependencies to global Cargo.toml, and then set workspace=true in specific package
Try solving with existing dependencies before adding new ones
Prefer well-maintained crates from crates.io
Be mindful of allocations in hot paths
Prefer structured logging (wide logs with a bunch of useful fields)
Provide helpful error messages
Use #[test_case] when writing tests, and use snake_case for naming the tests
No need for bullshit tests (e.g. tautology)
Make sure tests are not flaky (no weird sleeps)
No inline magic numbers or strings
In tests const error/status messages and assert against the shared constant
Add #[derive(Copy)] only on structs with 1 primitive field
NO TRIVIAL COMMENTS

Testing

Cheapest first, and scope to the crate you touched while iterating:

just check (or cargo check -p <crate> --all-targets)
just lint - cargo clippy --all --all-targets --features maki-ui/bench -- -D warnings
just test - cargo nextest run --workspace

Read justfile for more.

Dev builds skip debug info for deps and vendored C (our crates keep it); to debug into a dep set [profile.dev.package.<name>] debug = true.

Read the full file on GitHub · 77 lines

Changes

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.

6d ago Changed 1e44068bbfd0
10d ago Changed · +11 tokens per session 266f98081c20
13d ago Changed · +2 lines · +123 tokens per session 167980d609ad
1mo ago Changed · -27 tokens per session afc19c712f2a
1mo ago Changed · +2 lines · +92 tokens per session 8bc70d0d8f64
1mo ago Changed · +4 tokens per session 91ddcc3c5026
2mo ago First seen · 73 lines · 898 tokens per session scan A 2202054d7673

Subscribe to this mod's changes

maki AGENTS.md is an instructions file published in the GitHub repository tontinton/maki (1,374 stars, last pushed yesterday), licensed MIT. It adds 1,101 tokens to every session, about $0.0044 per session on Opus 5.5. 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.

maki AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
maki AGENTS.mdtontinton/maki	Instructions file	1.4k	yesterday	MIT	A	1,101	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

maki: Instructions file for Codex