clud-review SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
clud-review from talos-hq/clud is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add talos-hq/clud/clud-review@git:20261029.36aeb00Pins git:20261029.36aeb00 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- talos-hq/clud
- Path
crates/clud-bin/assets/skills/clud-review/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261029.36aeb00, committed Oct 29, 2026
- First version recorded
- Aug 4, 2026
- Size
- 25,372 bytes
- Repository stars
- 16
- License
- a license file GitHub does not identify
Pre-push code review gate. Inventories changed files, groups them by language bucket, and gives one primary reviewer every non-empty bucket plus all applicable repository rules. An invocation-wide budget of one covers retries and follow-ups. Discovers .coderabbit.yaml, repo review skills/agents, CLAUDE.md/AGENTS.md guidance, and optionally runs the originating issue's focused test for RED -> GREEN validation. Read-only; run standalone, or called by /clud-fix-quick or a /goal run before `gh pr…
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
<!-- managed-by: clud --> # /clud-review Keep tool output bounded (narrow searches, capped lists, ranged reads, bulk on disk, no identical repeats): https://github.com/zackees/clud/blob/main/docs/architecture/bounded-output.md Pre-push review gate that inventories the worktree's local diff, classifies the changed files by language family, gives one primary reviewer every non-empty bucket using the project's actual rules, and aggregates findings into a single Markdown table. Optionally runs the originating issue's focused test for local RED -> GREEN validation. `/clud-review` is the loop step the human reviewer would run if they could be summoned at every push — same content they'd see, same rules they'd apply, returned in seconds instead of days. For code changes, the caller preserves RED -> GREEN: identify or add the focused failing test/repro first, implement the scoped change, then rerun that focused signal until it passes before broad gates. `/clud-review` ITSELF never edits code — it surfaces findings; the caller's existing fix loop turns them GREEN. Where the originating issue's focused test is discoverable, the …
Read the whole file at its exact version.
How to install
mdr add talos-hq/clud/clud-review@sha256:05bcb62e745dab55The line at the top of this page pins the label git:20261029.36aeb00, 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_ott5o34yolvxfo4q)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 4, 2026 and Oct 29, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261029.36aeb00 latest | 2026-10-29 | 36aeb00 | 25,372 B | A | view · diff |
| git:20261028.1d1ca1c | 2026-10-28 | 1d1ca1c | 25,158 B | A | view · diff |
| git:20261003.5ee4059 | 2026-10-03 | 5ee4059 | 24,736 B | A | view · diff |
| git:20261001.ed53bdb | 2026-10-01 | ed53bdb | 24,255 B | A | view · diff |
| git:20260929.3fd0596 | 2026-09-29 | 3fd0596 | 24,068 B | A | view · diff |
| git:20260807.dd89e45 | 2026-08-07 | dd89e45 | 23,401 B | A | view · diff |
| git:20260804.8278017 | 2026-08-04 | 8278017 | 23,718 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 (25372 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
talos-hq/clud · 16 stars · license a license file GitHub does not identify · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ott5o34yolvxfo4q GET https://markdownregistry.com/api/v1/resolve?ref=talos-hq/clud/clud-review GET https://markdownregistry.com/api/v1/blob/05bcb62e745dab55f10bbf530b20cbca8a7d37276543ffde1fbdc357dd981063
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.