pilot-patch-and-drift SKILL.md skillA
pilot-patch-and-drift from confighub/cub-scout is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add confighub/cub-scout/pilot-patch-and-drift@git:20260926.4c4b67cPins git:20260926.4c4b67c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- confighub/cub-scout
- Path
skills/pilot-patch-and-drift/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260926.4c4b67c, committed Sep 26, 2026
- First version recorded
- May 22, 2026
- Size
- 20,775 bytes
- Repository stars
- 14
- License
- MIT
Use when Pilot is CLASSIFYING DRIFT and DECIDING WHAT TO DO ABOUT IT after a divergence between intended state and live state is detected. Natural phrasings: "Pilot, classify this drift", "is this manual edit or controller drift?", "should Pilot revert this patch?", "quarantine or accept-as-canonical?", "what does cub-scout say about who touched this field?", "render a drift verdict for the audit". Pilot consumes cub-scout''s attribution evidence (`cause: manual-edit` / `controller-drift` /…
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
# pilot-patch-and-drift The drift-classification scenario from **Pilot's** side. A field has diverged from its intended value; Pilot needs to decide what to do — revert, quarantine, accept-as-canonical, or ASK a human. The decision depends on **who** changed the field and **what kind** of change it was, which is exactly what cub-scout's attribution layer (#435) produces. cub-scout's attribution surface is deterministic: every `compareFieldMismatch` carries `cause` (`controller-drift` / `manual-edit` / `unknown`) + `managerHint` (the verified manager-string from `managedFields`) + `gitSource` (where the intended value came from) + `bindingSource` (which ConfigHub Link supplied it, when connected). Pilot reads that triple and picks an action. ## When to use Explicit phrasings: - "Pilot, classify this drift" - "Is this manual edit or controller drift?" - "Should Pilot revert this patch?" - "Quarantine or accept-as-canonical?" - "What does cub-scout say about who touched this field?" - "Render a drift verdict for the audit" - "Decision: is this an emergency manual fix we accept, or noise we revert?" - "Argo and kubectl both wrote this field — who actually owns it?" …
Read the whole file at its exact version.
How to install
mdr add confighub/cub-scout/pilot-patch-and-drift@sha256:85f64ad09675d8a0The line at the top of this page pins the label git:20260926.4c4b67c, 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_hlvfb4xym3tyf3yv)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between May 22, 2026 and Sep 26, 2026, about one every 42 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260926.4c4b67c latest | 2026-09-26 | 4c4b67c | 20,775 B | A | view · diff |
| git:20260624.e6ab578 | 2026-06-24 | e6ab578 | 20,579 B | A | view · diff |
| git:20260522.82ceddc | 2026-05-22 | 82ceddc | 20,471 B | A | view · diff |
| git:20260522.7d424d1 | 2026-05-22 | 7d424d1 | 18,903 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 (20775 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
confighub/cub-scout · 14 stars · license MIT · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hlvfb4xym3tyf3yv GET https://markdownregistry.com/api/v1/resolve?ref=confighub/cub-scout/pilot-patch-and-drift GET https://markdownregistry.com/api/v1/blob/85f64ad09675d8a0a0140b39b06203e082d20e418e4470a906d8bb9dfa5daf75
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.