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 skills add mattwynne/yaks --skill yak-mappinggit 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/skills/mattwynne/yaks/yak-mapping)<a href="https://agentmods.dev/skills/mattwynne/yaks/yak-mapping"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/yak-mapping/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/skills/mattwynne/yaks/yak-mapping"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/yak-mapping.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 | $0.00019 | $0.02830 |
| Opus 5 | $0.00010 | $0.01415 |
| Sonnet 5 | $0.00004 | $0.00566 |
| Haiku 4.5 | $0.00002 | $0.00283 |
Grade C, and why
yak-mapping 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 10d 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: `rm -rf .yaks`, `mkdir .yaks/...`, `cat > .yaks/...` How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yak Mapping
Overview
Yak mapping is emergent planning through action. You discover work structure by approaching goals and finding what blocks you, not by decomposing from the top down.
Core principle: "It is in the doing of the work that we discover the work that we must do." — Woody Zuill
Announcement
Always start yak mapping by saying:
"I'm using yak-mapping to discover the work structure by approaching the goal. I'll add yaks one at a time and show the map after each addition."
This sets expectations that we're doing emergent discovery, not top-down planning.
When to Use
Use when:
- User asks you to "plan" or "map out" work using yaks
- User says "adapt for yaks" or "plan with yaks" or "break down into yaks"
- User wants to structure work using the yak tool (this project)
- Starting to structure a new feature or goal
- Need to break down complex work
NOT for writing plan documents - this creates actual yaks, not markdown plans.
Don't use when:
- Just executing already-mapped work
- Single straightforward task
- User provides detailed step-by-step plan
CRITICAL: Use yx CLI Only
NEVER touch .yaks directory directly!
- Use:
yx add,yx move,yx rm,yx context - Never:
rm -rf .yaks,mkdir .yaks/...,cat > .yaks/...
This is dogfooding - we use yaks to build yaks.
THE IRON LAW
After EVERY yx add, immediately run yx ls to show what changed.
No exceptions:
- Not "I'll show it at the end"
- Not "just adding a quick one"
- Not "the structure is obvious"
yx add then yx ls is non-negotiable. This keeps the human in sync with your thinking.
The Approach Pattern
Phase 1: Scope the Goal (BEFORE creating child yaks)
After creating the top-level goal yak, have a conversation to agree scope before going deeper. Don't start adding children yet.
- Add the goal yak and show the map
- Summarise your understanding of the goal back to the human
- Present candidate areas you've identified (if any), but as a conversation — NOT as yaks yet
- Ask the human to pick what's in scope for now. Use AskUserQuestion or just ask directly.
- Only after agreement, start the discovery loop on the agreed scope
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.
- 10d ago First seen · 385 lines · 19 tokens per session scan C c44bdc69efea
yak-mapping is a skill published in the GitHub repository mattwynne/yaks (58 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 2,830 once invoked, about $0.0001 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 skills, from other repositories
skill-creator
Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.
skill-index-updater
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).
hello-world
A minimal test skill that greets the user and demonstrates the ASM publish workflow.
openagents-workspace
OpenAgents Workspace collaboration tools — shared files, browser, and multi-agent coordination. Use when: sharing files or reports, browsing websites, reading shared files, checking workspace agents, or collaborating with other agents via @mentions.
refresh-index
Sync every enabled repo in the curated skill index and open a confirmation-gated PR. Use when refreshing already-indexed sources. Don't use for adding new repos, improving a single skill, or installing skills locally.
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.