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 parallel-yak-implementationgit 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/parallel-yak-implementation)<a href="https://agentmods.dev/skills/mattwynne/yaks/parallel-yak-implementation"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/parallel-yak-implementation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.00660 |
| Opus 5 | $0.00015 | $0.00330 |
| Sonnet 5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
parallel-yak-implementation 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Yak Implementation
Overview
When multiple leaf yaks are independent and have plans, dispatch
one agent per yak in parallel worktrees. This skill wraps
superpowers-dev:dispatching-parallel-agents with yak-specific
lifecycle steps.
When to Use
- 2+ leaf yaks are ready (have plans, no children)
- The yaks don't modify the same files
- You want to maximize throughput
The Process
1. Identify Ready Leaves
yx ls
Leaf yaks (no children) with plans are candidates. Verify independence: check their plans don't touch the same files.
2. Mark ALL as WIP Before Dispatching
This is the FIRST thing you do after identifying yaks.
yx state "<yak-name>" wip
Do this for EVERY yak BEFORE launching any agents. This signals to the human (and future sessions) what's being worked on.
Verify with yx ls - all target yaks should show as wip
before you proceed to step 3.
3. Dispatch One Agent Per Yak
REQUIRED: Use superpowers-dev:dispatching-parallel-agents
for the dispatch pattern.
Each agent prompt should include:
- The yak's plan (from
yx field --show "<name>" plan) - Instruction to invoke
superpowers-dev:using-git-worktrees - Instruction to invoke
superpowers-dev:executing-plans - Project context (test commands, commit conventions)
- Clear scope: only work on this yak's files
4. When Agents Complete
For each returning agent:
- Review the summary
- Verify with
dev checkin the worktree - Mark yak done:
yx state "<name>" done - Use
superpowers-dev:finishing-a-development-branch
If an agent fails, keep the yak as wip and investigate.
⛔ The Main Branch Rule
Neither you nor your subagents may modify main's working tree. Main is for merging finished branches only.
- Subagents must each work in their own worktree
- The orchestrating agent (you) must not stash, clean, or edit files on main
- If you see uncommitted changes on main, stop and ask the user — they belong to someone else
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.
- 8d ago First seen · 93 lines · 29 tokens per session scan A abc6f2b23a54
parallel-yak-implementation is a skill published in the GitHub repository mattwynne/yaks (58 stars, last pushed 26d ago), licensed MIT. It adds 29 tokens to every session and 660 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
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
pbt-strategy
Property-based testing with Python Hypothesis — find invariants, write @given strategies, and model stateful systems with RuleBasedStateMachine.
debug
Systematic root-cause debugging — reproduce, isolate, hypothesize, fix with TDD.
issue-driven-development
Use for any development work - the master 13-step coding process that orchestrates all other skills, ensuring GitHub issue tracking, proper branching, TDD, code review, and CI verification.
tdd-full-coverage
Use when implementing features or fixes - test-driven development with RED-GREEN-REFACTOR cycle and full code coverage requirement.