cross-review SKILL.md skillA
cross-review from broomva/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add broomva/skills/cross-review@git:20261009.58d7a2fPins git:20261009.58d7a2f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- broomva/skills
- Path
skills/governance/cross-review/SKILL.md- Versions recorded
- 12
- Latest version
- git:20261009.58d7a2f, committed Oct 9, 2026
- First version recorded
- Aug 21, 2026
- Size
- 55,526 bytes
- Repository stars
- 4
- License
- MIT
bstack P20 — Cross-Model Adversarial Review Gate. The model that wrote the code cannot be the final judge of the code. Before substantive PRs merge, fire a cross-model adversarial gate — different evaluator than writer, anti-slop scoring ≥7/10, a dynamic round budget (3 free, 4-7 earned by a continuation verdict carrying a falsifiable prediction, >=8 human), verdict logged in PR. Three strata: (A) Codex CLI cross-vendor for true different-model verdict, (B) fresh-context subagent under…
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
# cross-review — bstack P20 Cross-Model Adversarial Review Gate **The writer cannot be the final judge of the work.** When the same AI model plans, implements, and reviews, it will not challenge its own assumptions. It has systematic blind spots baked into its training. A different model — trained differently, with different biases and pattern preferences — catches what the first one misses. `cross-review` is the bstack gate that enforces this discipline. Substantive PRs cannot merge until a *different evaluator* than the writer scores the work ≥ 7/10 against an anti-slop rubric. ## Origin Inspired by [Dallionking/cross-model-agents](https://github.com/Dallionking/cross-model-agents) (May 2026) — 31-agent bidirectional Claude↔Codex review system. That project ships specific agents and hooks. `broomva/cross-review` absorbs the *discipline* while composing with the existing bstack adversarial-review skill toolkit. ## Reviewing a design rather than a diff When the artifact is a spec, plan, ADR or RFD — the `--spec` flag below — the anti-slop rubric is the wrong instrument: it scores code. Use **`spec-contract`** instead, which is this gate applied to a design: …
Read the whole file at its exact version.
How to install
mdr add broomva/skills/cross-review@sha256:4b947aa375218d03The line at the top of this page pins the label git:20261009.58d7a2f, 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_phjxezqtnlvdjsyp)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 12 versions of this file, between Aug 21, 2026 and Oct 9, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261009.58d7a2f latest | 2026-10-09 | 58d7a2f | 55,526 B | A | view · diff |
| git:20261006.5be6bde | 2026-10-06 | 5be6bde | 54,119 B | A | view · diff |
| git:20260928.3fa6584 | 2026-09-28 | 3fa6584 | 49,611 B | A | view · diff |
| git:20260927.4a136db | 2026-09-27 | 4a136db | 48,248 B | A | view · diff |
| git:20260924.0c1ec97 | 2026-09-24 | 0c1ec97 | 45,667 B | A | view · diff |
| git:20260917.b709d10 | 2026-09-17 | b709d10 | 45,494 B | A | view · diff |
| git:20260914.240dd1f | 2026-09-14 | 240dd1f | 43,268 B | A | view · diff |
| git:20260824.792720f | 2026-08-24 | 792720f | 39,020 B | A | view · diff |
| git:20260824.acb8d22 | 2026-08-24 | acb8d22 | 38,656 B | A | view · diff |
| git:20260823.81d5f46 | 2026-08-23 | 81d5f46 | 37,230 B | A | view · diff |
| git:20260821.b36c0ec | 2026-08-21 | b36c0ec | 26,654 B | A | view · diff |
| git:20260821.2694c3e | 2026-08-21 | 2694c3e | 26,646 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 (55526 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
broomva/skills · 4 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_phjxezqtnlvdjsyp GET https://markdownregistry.com/api/v1/resolve?ref=broomva/skills/cross-review GET https://markdownregistry.com/api/v1/blob/4b947aa375218d03d655f06d5657ad2e1f5cd61b979889ba1cf520533945b263
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.