work

work is a skill for Claude Code, Codex from mattwynne/yaks. It costs 25 tokens per session (2,383 once invoked), scanned A, original, MIT.

A workflow skill for implementing ready tasks called yaks by sending them to agents in separate Git worktrees and merging completed work back.

In plain words
What is it for?
Use it when ready, well-defined yaks exist and need implementation. A Git worktree is a separate working copy connected to the same repository.
Why use it?
It organizes implementation work and keeps the main working area unchanged while agents build and verify individual tasks.

Skill for Claude CodeCodex

Part of the yx plugin — 3 skills shipped together

Install

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.

agentmods
npx agentmods add skills/mattwynne/yaks/work
Any agent
npx skills add mattwynne/yaks --skill work
Clone the repo
git clone --depth 1 https://github.com/mattwynne/yaks

Made for: Claude Code, Codex.

Or install yx, the plugin that ships this one along with the rest of its 3 skills.

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.

agentmods badge for work

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattwynne/yaks/work.svg)](https://agentmods.dev/skills/mattwynne/yaks/work)
Your own site
<a href="https://agentmods.dev/skills/mattwynne/yaks/work"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/work.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.02383
Opus 5 $0.00013 $0.01192
Sonnet 5 $0.00005 $0.00477
Haiku 4.5 $0.00003 $0.00238

Measured 5d ago against content hash b6a61a67d502, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

work 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 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.

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.

plugins/yx/skills/work/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/yx:work — Working on Yaks

Overview

You orchestrate; subagents implement. Each leaf yak gets its own worktree and branch. When the subagent finishes and verification passes, you merge back to main.

The golden rule: Neither you nor your subagents may modify main's working tree.

When invoked with arguments (e.g., /yx:work fix auth bug), use those to identify which yak to work on.

Always announce: "I'm using /yx:work to implement leaf yaks in isolated worktrees. I'll merge back to main once verification passes."

When to Use

Use when:

  • User asks to "implement", "work on", or "pick up" yaks
  • Ready leaf yaks exist (has context, no @needs-human tag, no children)
  • User wants to start building after mapping or preparing

Don't use when:

  • No leaf yaks exist yet (use /yx:map first)
  • Yaks lack context or clear definition of done (use /yx:prepare first)
  • User is just exploring or planning (not ready to implement)

What This Skill Owns vs What the Project Owns

This Skill Owns

  • Yak lifecycle (identify ready leaves, mark wip/done, handle @needs-human tags)
  • Worktree management (create, cleanup, ensure main is never modified)
  • Orchestration (dispatch subagents, review output, determine independence for parallel work)
  • Merging (verify, merge to main, clean up branches)

The Project Owns

  • Implementation practices: TDD, code review, commit messages, etc. — defer to project conventions
  • Verification: Before merging, run the project's verification (tests, linting, CI checks). Check CLAUDE.md for "done" criteria
  • Code quality: The subagent decides how to implement, what tests to write, how to refactor

The key: This skill provides structure; the project provides standards. Always check CLAUDE.md or project docs for verification requirements.

THE MAIN BRANCH RULE

Neither you nor your subagents may modify main's working tree. Main is for merging finished branches only.

  • Subagents work in their own worktrees
  • You (orchestrating agent) never edit files on main
  • If uncommitted changes exist on main, STOP and ask the user

Read the full file on GitHub · 284 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.

  1. 5d ago First seen · 284 lines · 25 tokens per session scan A b6a61a67d502

Subscribe to this mod's changes

work is a skill published in the GitHub repository mattwynne/yaks (58 stars, last pushed 24d ago), licensed MIT. It adds 25 tokens to every session and 2,383 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.