instar-dev
Instar-specific development skill used by the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities).
Connecting the steps of a workflow
What it does
Audience: this skill is for the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities). It is NOT a user-facing skill.
Read more
End users of instar should never invoke /instar-dev and will never see it in their workflow — it runs at the infrastructure-developer layer, not the per-user application layer. The enforcement hooks on the instar repo ensure the instar-developing agent goes through this skill for every change, but end users never encounter it.
What it can touch
Includes 2 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/verify-proposal-derived-runbook.mjs, scripts/write-trace.mjs.
1 smaller thing worth knowing
Sets itself up to run again automatically later. Usually legitimate — listed so nothing is hidden.
How we know
Sets itself up to run again automatically later — scripts/write-trace.mjs line 223. Read 2026-10-04, commit 34e691b.
scripts/write-trace.mjs, line 223 ↗No serious risk pattern found
Launch7’s automated check read all 5 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-04, commit 34e691b by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to JKHeadley/instar: 2026-10-04 (0 days before the scan).
Read automatically from the skill’s own files on GitHub on 4 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 2 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 JKHeadley
All from this publisher →- spec-converge
Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration,…
- test-as-self
Verifying Part 1 of the spec — does the server actually auto-demote to send-only when the lifeline owns the poll slot?
