autoreview SKILL.md skillA

autoreview from vincentkoc/tokenjuice is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add vincentkoc/tokenjuice/autoreview@git:20260523.2e84b1b

Pins git:20260523.2e84b1b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
vincentkoc/tokenjuice
Path
.agents/skills/autoreview/SKILL.md
Versions recorded
1
Latest version
git:20260523.2e84b1b, committed May 23, 2026
Size
7,576 bytes
Repository stars
527
License
MIT

Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.

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

# Auto Review

Run the bundled structured review helper as a closeout check. This is code review, not Guardian `auto_review` approval routing.

Codex review is the default when no engine is set. It usually delivers the best review results and should remain the normal final closeout engine.

Use when:

- user asks for Codex review / Claude review / autoreview / second-model review
- after non-trivial code edits, before final/commit/ship
- reviewing a local branch or PR branch after fixes

## Contract

- Treat review output as advisory. Never blindly apply it.
- Verify every finding by reading the real code path and adjacent files.
- Read dependency docs/source/types when the finding depends on external behavior.
- Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase.
- Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class.
- Keep going until structured review returns no accepted/actionable findings.
- If a review-triggered fix changes code, rerun focused tests and rerun the structured review helper.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add vincentkoc/tokenjuice/autoreview@sha256:5022ca875c7f77eb

The line at the top of this page pins the label git:20260523.2e84b1b, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wbpdptdbdg2ollh7.svg)](https://markdownregistry.com/a/art_wbpdptdbdg2ollh7)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 23, 2026.

versioncommittedcommitsizeaudit
git:20260523.2e84b1b latest2026-05-23 2e84b1b 7,576 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7576 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

GitHub

vincentkoc/tokenjuice · 527 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wbpdptdbdg2ollh7
GET https://markdownregistry.com/api/v1/resolve?ref=vincentkoc/tokenjuice/autoreview
GET https://markdownregistry.com/api/v1/blob/5022ca875c7f77eb4ad32943a920c479b2344095f5453b93dc68a15389bb714c

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.

More from vincentkoc/tokenjuice

AGENTS.md AGENTS.md file
vincentkoc/tokenjuice · AGENTS.md
git:20261028.1d7ae47 · audit A · 527 stars
tokenjuice SKILL.md skill
vincentkoc/tokenjuice · packaging/skills/doubao-work/tokenjuice/SKILL.md · Compact noisy terminal output with tokenjuice while preserving exact-read and failure semantics.
git:20261031.95d6713 · audit A · 527 stars
tokenjuice SKILL.md skill
vincentkoc/tokenjuice · packaging/skills/workbuddy/tokenjuice/SKILL.md · Use tokenjuice when terminal commands produce noisy output.
v1.0.0 · audit A · 527 stars

Every file in vincentkoc/tokenjuice

Other files named autoreview

autoreview SKILL.md skill
openclaw/clawhub · .agents/skills/autoreview/SKILL.md · Structured code review through the shared OpenClaw agent-skills installation.
git:20261020.ec1016a · audit A · 9,544 stars
autoreview SKILL.md skill
amd/gaia · tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md · Pre-commit/ship code review: Codex default; optional Claude or Pi.
git:20260812.c83047b · audit A · 1,601 stars
autoreview SKILL.md skill
openclaw/crabbox · .agents/skills/autoreview/SKILL.md · Structured code review through the shared OpenClaw agent-skills installation.
git:20261006.d614384 · audit A · 1,513 stars
autoreview SKILL.md skill
openclaw/agent-skills · skills/autoreview/SKILL.md · Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.
git:20261103.c7cde4a · audit A · 1,114 stars
autoreview SKILL.md skill
swyxio/skills · autoreview/SKILL.md · Perform a structured final code review of a local diff, commit, branch, or pull request. Use only when the user…
git:20260809.243a0c6 · audit A · 194 stars
autoreview SKILL.md skill
openclaw/clawscan · .agents/skills/autoreview/SKILL.md · Structured code review through the shared OpenClaw agent-skills installation.
git:20261020.5be7f8e · audit A · 151 stars
autoreview SKILL.md skill
anantys-oss/koan · koan/skills/core/autoreview/SKILL.md · Toggle automatic review+rebase after PR creation per project
v1.0.0 · audit A · 48 stars
autoreview SKILL.md skill
simonrowland/goal-flight · autoreview/SKILL.md · Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit…
git:20260923.0d635f8 · audit A · 20 stars

Browse by kind, by grade A, or by owner.