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/mattwynne/yaks/agents-mdgit clone --depth 1 https://github.com/mattwynne/yaksWrote 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/mattwynne/yaks/agents-md)<a href="https://agentmods.dev/instructions/mattwynne/yaks/agents-md"><img src="https://agentmods.dev/badge/instructions/mattwynne/yaks/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 5.1 | $0.01106 | $0.01106 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade C, and why
yaks AGENTS.md scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **NEVER**: Run `rm -rf .yaks` or modify `.yaks` contents directly How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This file provides guidance to Agents working in this repository.
We use yaks for task tasking. See !yx help
See CONTRIBUTING for dev tooling and commands.
Architecture
Hexagonal architecture with CQRS and Event Sourcing. Commands flow
through use cases to the YakMap aggregate, which emits domain events.
Events are persisted to git refs and projected to the .yaks/
directory-based read model.
See src/README.md for the full architecture
guide: layers, key types, ports, adapters, and how commands flow.
See docs/adr/ for Architecture Decision
Records explaining why the design is the way it is.
When making architectural decisions, invoke the cqrs-event-sourcing
skill for guidance on aggregate boundaries, event design, read models,
policies, and sagas.
Testing layers
- Cucumber acceptance tests (
features/*.feature): For executable specifications, agreed with human partner. Dual-mode execution viacargo test --test cucumber --features test-support:- FullStackWorld: spawns yx binary (real integration test)
- InProcessWorld: calls Rust directly with in-memory adapters (fast)
- ShellSpec tests (
tests/shellspec/): For tests that don't fit Cucumber (tmux smoke, git checks, installer). Run withshellspec. - Rust unit tests: Internal logic (
cargo test)
Mutation Testing
Validates test quality by injecting code changes and checking tests catch them.
dev mutate-diff # Fast: only mutants in your changes (~seconds)
dev mutate # Full run (~7 min, ~400 mutants)
dev mutate -F 'slug' # Full run filtered to specific files
dev mutate-sync # Sync missed mutants to yaks
Daily workflow: Use dev mutate-diff (alias dev md) while coding.
After a full run: dev mutate-sync (alias dev ms) creates yaks
for missed mutants. Then yx sync to share results.
Config: .cargo/mutants.toml excludes infrastructure-only files.
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 · 126 lines · 1,106 tokens per session scan C 10e05ff2117a
yaks AGENTS.md is an instructions file published in the GitHub repository mattwynne/yaks (58 stars, last pushed 24d ago), licensed MIT. It adds 1,106 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
asm AGENTS.md
AGENTS.md instructions for luongnv89/asm, covering agents.md, when to delegate, definitions, shared boundaries and editing this file.
asm CLAUDE.md
Claude Code instructions for luongnv89/asm, covering claude.md, critical commands, architecture map, hard rules and workflow preferences.
beads AGENTS.md
AGENTS.md instructions for gastownhall/beads, covering agent instructions, key sections, project scope, pr safety for agents and visual design anti-patterns.
remind AGENTS.md
Instructions for sandst1/remind, covering remind - development guide for ai agents, project overview, architecture, key abstractions and data models (models.py).
agentor CLAUDE.md
Claude Code instructions for lonetis/agentor, covering agent orchestrator (agentor), architecture, detailed documentation, tech stack and dev commands.
agent-spaces CLAUDE.md
Claude Code instructions for hunmer/agent-spaces, covering agent spaces, 约定, 文件索引, 模块索引 and 扫描状态.