helm SKILL.md skillA
helm from jimuelle07/helm is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jimuelle07/helm/helm@git:20260920.5ea81c6Pins git:20260920.5ea81c6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jimuelle07/helm
- Path
skills/helm/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260920.5ea81c6, committed Sep 20, 2026
- First version recorded
- Sep 20, 2026
- Size
- 19,977 bytes
- Repository stars
- 17
- License
- MIT
Routes a coding task to the best AI agent installed on this machine. Probes which agent CLIs are installed AND logged in - Claude Code, Codex, Cursor Agent, Gemini CLI, Aider, OpenCode, GitHub Copilot, Amp, Droid, Crush, Goose, Qwen Code, Ollama and local models - reads CPU/RAM/VRAM, then uses TypeSafe Jev, its required typed decision layer, to choose one, dispatch the task and judge whether the worker finished. Use it for: which model or agent should handle this; what agents or models do I…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Helm *Taking the helm of the agents already on your machine.* Built by [Jimuelle Patron](https://github.com/Jimuelle07) · MIT · [github.com/Jimuelle07/Helm](https://github.com/Jimuelle07/Helm) Helm is an orchestration harness: it inventories the coding agents installed on this machine (`probe.py`), routes a task to the best one (`route.py`), dispatches it and judges whether the work actually got done (`supervise.py`). The routing and the judging are done by **TypeSafe Jev**, a typed decision model — that is what lets the orchestration run on every task instead of only the expensive ones. ## Why this exists An LLM does not know its own tools unless they are called. A coding agent learns what it can do from a tool list in its prompt, so the six other agent CLIs sitting in the same `PATH` — each with a different model, price, context window, and speciality — are simply invisible to it. Worse, when an agent does stray outside its competence, it finds out by *failing*: attempt, burn tokens, retry, apologise. The knowledge is produced after paying for it, then thrown away when the session ends. This skill fixes that by splitting the problem into three jobs and giving each to the …
Read the whole file at its exact version.
How to install
mdr add jimuelle07/helm/helm@sha256:608a8ab5a45fd329The line at the top of this page pins the label git:20260920.5ea81c6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_57apfdrgnw6762eu)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, all committed on Sep 20, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260920.5ea81c6 latest | 2026-09-20 | 5ea81c6 | 19,977 B | A | view · diff |
| git:20260920.f5dafc3 | 2026-09-20 | f5dafc3 | 19,820 B | A | view · diff |
| git:20260920.5d2287c | 2026-09-20 | 5d2287c | 16,193 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (19977 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jimuelle07/helm · 17 stars · license MIT · pushed 2026-09-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_57apfdrgnw6762eu GET https://markdownregistry.com/api/v1/resolve?ref=jimuelle07/helm/helm GET https://markdownregistry.com/api/v1/blob/608a8ab5a45fd3299fdd3522d3e0f6043d6117152bdfc1201156676bcfe8ed3c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.