prun
Use prun when the task splits into independent units that can run at once (different modules, separate research questions, parallel…
Connecting the steps of a workflow
What it does
prun fans a task out into independent units that run in parallel on separate-quota or in-session workers, while the Claude session only coordinates.
Read more
Workers are Codex (codex exec, a separate abundant account, frontier model) and Sonnet subagents (inside the Claude session). Codex is the prioritized default: its quota is separate from the Claude plan and its current model (gpt-5.6 tier) is strong on hard reasoning and code, so most units go to Codex. Sonnet is reserved for units that need something the Claude session uniquely provides (see the Executors rule). The coordinator decomposes the task, dispatches the units, gathers their results, reviews their diffs, and integrates. It never runs a unit itself.
What it can touch
Includes 10 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: scripts/dispatch-task-agy.py, scripts/gather.ps1, scripts/gather.sh, scripts/monitor.ps1….
Asks for an API key or token
You will need an account with the service it talks to, and your own key. Keep keys in your settings or environment, never in a chat.
How we know
The SKILL.md mentions an API key or access token.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Turns off your AI's permission prompts
This weakens the protection between the skill and your computer, so later steps can happen without you being asked.
How we know
SKILL.md line 153 (and 1 more in that file): “…o `--mode` it runs `accept-edits` with `--dangerously-skip-permissions` in a scratch directory it creates. A caller-supplied workspace, me…”. Read 2026-10-05, commit f7ddc0f.
SKILL.md, line 153 ↗Turns off your AI's permission prompts
This weakens the protection between the skill and your computer, so later steps can happen without you being asked.
How we know
scripts/dispatch-task-agy.py line 10 (and 2 more in that file): “``--dangerously-skip-permissions``, the same unattended capability the”. Read 2026-10-05, commit f7ddc0f.
scripts/dispatch-task-agy.py, line 10 ↗1 smaller thing worth knowing
Collects all of your environment variables. Usually legitimate — listed so nothing is hidden.
How we know
Collects all of your environment variables — scripts/dispatch-task-agy.py line 227. Read 2026-10-05, commit f7ddc0f.
scripts/dispatch-task-agy.py, line 227 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to yzhao062/anywhere-agents: 2026-10-03 (2 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 10 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from yzhao062
All from this publisher →- ci-mockup-figure
Create space-efficient figures for papers and proposals.
- my-router
Context-aware router that detects work type and dispatches to the right skill.
- readme-polish
A README is a text wall with no visual anchors and no one can tell what the project does from a first glance.
