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 skills/mattwynne/yaks/mapnpx skills add mattwynne/yaks --skill mapgit clone --depth 1 https://github.com/mattwynne/yaksWhat 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 | $0.00022 | $0.02731 |
| Opus 5 | $0.00011 | $0.01366 |
| Sonnet 5 | $0.00004 | $0.00546 |
| Haiku 4.5 | $0.00002 | $0.00273 |
Grade A, and why
map 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 yesterday.
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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yx:map — 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
When invoked with arguments (e.g., /yx:map build a REST API), use those as the initial goal.
Announcement
Always start yak mapping by saying:
"I'm using /yx:map 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 to "plan" or "map out" work using yaks
- User says "adapt for yaks" or "plan with yaks" or "break down into yaks"
- Starting to structure a new feature or goal
- Need to discover work structure for complex work
- User provides a goal and you need to find blockers
Don't use when:
- Just executing already-mapped work (use
/yx:work) - Single straightforward task (just do it)
- User wants detailed specs (use
/yx:preparefor fleshing out individual 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
- Only after agreement, start the discovery loop on the agreed scope
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 361 lines · 22 tokens per session scan A ba715ce820d7
map is a skill published in the GitHub repository mattwynne/yaks (54 stars, last pushed 20d ago), licensed MIT. It adds 22 tokens to every session and 2,731 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
beads
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or…
gsd
Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents.
Asana Automation
Automate Asana project management workflows, task tracking, team collaboration, and reporting.
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
to-prd
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
collavre
Manage Collavre Creatives (hierarchical tasks/content blocks) via CLI. Use when creating, retrieving, updating, importing, or batch-operating on Creatives. Creatives are tree-structured items with automatic progress rollup — like a smart to-do list that doubles as a structured document.