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/preparenpx skills add mattwynne/yaks --skill preparegit 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 | $0.00020 | $0.02506 |
| Opus 5 | $0.00010 | $0.01253 |
| Sonnet 5 | $0.00004 | $0.00501 |
| Haiku 4.5 | $0.00002 | $0.00251 |
Grade A, and why
prepare 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare Skill
You're helping prepare a yak for implementation. This is the bridge between mapping (lightweight structure) and working (hands-on implementation).
Arguments: $ARGUMENTS — the yak name to prepare, or empty to prompt the user.
Goal: Transform a yak from an idea into a well-specified piece of work ready for zero-context implementation.
When to Use This Skill
- User says "prepare this yak", "spec out X", "flesh out this work", "break down this feature"
- A yak needs more detail before implementation can start
- You need to establish acceptance criteria for a yak
- A yak is too big and needs breaking into sub-yaks
Related skills:
/yx:map— for lightweight initial structure and exploration/yx:work— for implementation after preparation is complete
Workflow reference: See ../docs/yak-workflow.dot for the overall yak lifecycle.
The Preparation Flow
1. Read Existing State
Before doing anything else, understand what you're working with:
# Show the yak details
yx show "$ARGUMENTS"
# See the context around it
yx ls
# Check parent and sibling yaks for context
If you need to explore the codebase (understand existing code, find relevant files, assess complexity):
- Delegate to a subagent — keeps the main conversation clean for spec discussion with the user
- Use explorers or code-reading agents to gather information
- Bring back a summary, not a transcript
Ask: Does the user want to answer questions now, or should you gather more context first?
2. Check for @needs-human
If the yak has a @needs-human tag:
yx show "$ARGUMENTS" --format json | jq -r '.tags[]'
Surface it: "This yak has an open question in its context: [question]. Want to answer now, or should I prepare a different yak?"
If answered, remove the tag:
yx untag "$ARGUMENTS" @needs-human
3. Mark Work In Progress
Before making any changes or additions:
yx start "$ARGUMENTS"
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 · 377 lines · 20 tokens per session scan A 7a6d32e5d123
prepare is a skill published in the GitHub repository mattwynne/yaks (54 stars, last pushed 20d ago), licensed MIT. It adds 20 tokens to every session and 2,506 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.