cross-model SKILL.md skillA
cross-model from gufranco/claude-engineering-rules is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gufranco/claude-engineering-rules/cross-model@git:20261012.84ebb18Pins git:20261012.84ebb18 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gufranco/claude-engineering-rules
- Path
skills/cross-model/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261012.84ebb18, committed Oct 12, 2026
- First version recorded
- Aug 26, 2026
- Size
- 10,286 bytes
- Repository stars
- 3
- License
- MIT
Consult a different model for orthogonal reasoning on a consequential decision, especially when confident. Discovers whichever model CLI is installed rather than assuming a vendor. Use when the user says "second opinion", "cross-model", "ask another model", "stress-test this", "what am I missing", "red-team this decision", or before committing to an architecture, a schema, a security boundary, or anything hard to reverse. For a reversible local decision or routine implementation, proceed…
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
## Overview Different training data, different tuning, different sampling. The blindspots do not line up. That non-overlap is the entire product; agreement is a bonus, not the goal. Invoking this is a mark of rigor, not an admission of uncertainty. It means the decision was taken seriously enough to generate friction against it. ## The Key Inversion Consult **when the decision is consequential and you are confident.** Confidence is exactly where a blindspot hides, because there is nothing prompting a second look. A decision that already feels shaky gets scrutiny for free. The corollary: adversarial coverage from the same model shares its blindspots by construction. A subagent that reviews your reasoning is running the same priors that produced it. That is worth doing and it is not this. ## When to Use Consequential, regardless of confidence: - An architecture choice before committing, especially a public interface, a data model, or a service boundary. - A security-sensitive surface: authentication, tenant isolation, payment handling, anything reachable by an untrusted caller. - A schema change or migration, which is hard to reverse. …
Read the whole file at its exact version.
How to install
mdr add gufranco/claude-engineering-rules/cross-model@sha256:e965c682e70e1ea6The line at the top of this page pins the label git:20261012.84ebb18, 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_7xzuvakzrfsjo3rf)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 26, 2026 and Oct 12, 2026, about one every 47 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261012.84ebb18 latest | 2026-10-12 | 84ebb18 | 10,286 B | A | view · diff |
| git:20260826.2a6a0a7 | 2026-08-26 | 2a6a0a7 | 8,183 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 (10286 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
gufranco/claude-engineering-rules · 3 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7xzuvakzrfsjo3rf GET https://markdownregistry.com/api/v1/resolve?ref=gufranco/claude-engineering-rules/cross-model GET https://markdownregistry.com/api/v1/blob/e965c682e70e1ea6d2f624617ff85821b2470bbdd53235850406288fbff19d3d
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.