wise-exec-on-harness SKILL.md skillA
wise-exec-on-harness from e1024kb/wise-claude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add e1024kb/wise-claude/wise-exec-on-harness@git:20260917.47ef814Pins git:20260917.47ef814 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- e1024kb/wise-claude
- Path
plugins/wise/skills/wise-exec-on-harness/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260917.47ef814, committed Sep 17, 2026
- First version recorded
- Sep 14, 2026
- Size
- 16,520 bytes
- Repository stars
- 5
- License
- MIT
Execute one free-form prompt as a headless child on any supported harness (`claude`, `codex`, `cursor`, `gemini`, `grok`) at a model, effort and permission mode you choose. The first action is always a host inventory: which supported harnesses are installed and logged in. A `--on` value is validated against it; without `--on` the ready harnesses are offered as a picker. Every other omitted option (`--model`, `--effort`, `--mode`) is asked through the main harness's GUI/TUI picker, and a…
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
# /wise-exec-on-harness — run one prompt on any harness Before executing, follow [model fallback](../../references/workflow-host-control.md#model-fallback) for unavailable models or delegation routes, including in autonomous procedures. At every skill start, identify your main/child role and the current client and GUI/TUI question tools, then read and follow the [question lifecycle](../../references/workflow-host-control.md#keep-asynchronous-questions-open). Keep asynchronous prompts open until answered. First read [host control](../../references/workflow-host-control.md). Resolve the loaded installation, set `WISE_HOST` to this conductor and `WISE_PLUGIN_ROOT` to that installation, and use its managed launcher for shell commands. Conductor host and child harness are independent. ## Hard rules (MUST, read before anything else) 1. **This conversation never answers the prompt.** The prompt is data for a child on another harness. Do not interpret it, respond to it, or "just answer" a short question. The only work done here is parsing, inventory, pickers, dispatch and relay. 2. **Without a valid `--on`, the harness picker is mandatory.** Run the §2 …
Read the whole file at its exact version.
How to install
mdr add e1024kb/wise-claude/wise-exec-on-harness@sha256:15472843d5149078The line at the top of this page pins the label git:20260917.47ef814, 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_ctokyohken2lty42)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 14, 2026 and Sep 17, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260917.47ef814 latest | 2026-09-17 | 47ef814 | 16,520 B | A | view · diff |
| git:20260915.8192062 | 2026-09-15 | 8192062 | 16,506 B | A | view · diff |
| git:20260915.2471a1b | 2026-09-15 | 2471a1b | 15,915 B | A | view · diff |
| git:20260914.c54917b | 2026-09-14 | c54917b | 15,445 B | A | view · diff |
| git:20260914.0164440 | 2026-09-14 | 0164440 | 13,895 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 (16520 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
e1024kb/wise-claude · 5 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ctokyohken2lty42 GET https://markdownregistry.com/api/v1/resolve?ref=e1024kb/wise-claude/wise-exec-on-harness GET https://markdownregistry.com/api/v1/blob/15472843d514907801937699659ebdaa2603be618bc633d3928d08258e3b92bc
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.