Home / sandbaseai / sandbase-harness · examples/basic/skills/code-review/SKILL.md · GitHub

code-review skillA

code-review is agent-read markdown (skill) from sandbaseai/sandbase-harness: Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Code Review Skill

## When to use

Use this skill when a user provides source code, a patch, or a pull request and
wants a focused review. It is not a substitute for running the project's test
suite, a dedicated security audit, or human review of high-impact changes.

## Inputs

Ask for or identify:

- the file path, code block, diff, or pull request to review;
- the language and relevant project conventions, if known;
- the requested scope (correctness, security, performance, style, or all);
- any expected behavior or test evidence supplied by the user.

If the input is incomplete, state the limitation and review only the material
that is actually available.

## Procedure

1. Understand the intended behavior and boundaries before judging an excerpt.
2. Check correctness, edge cases, error handling, state changes, and API
   contracts.
3. Check security risks such as injection, authorization mistakes, secret
   exposure, unsafe deserialization, and untrusted input handling.
4. Check maintainability, performance risks, test coverage, and consistency
   with nearby code.
5. Report only actionable findings, ordered by severity. Distinguish confirmed
…

Read the whole file at its exact version.

How to install

Latest version
mdr add sandbaseai/sandbase-harness/code-review@git:20260830.0856d32
Exact content
mdr add sandbaseai/sandbase-harness/code-review@sha256:89c3d015f74599d5

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_uajv2cb3cbtpze2z.svg)](https://markdownregistry.com/a/art_uajv2cb3cbtpze2z)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260830.0856d32 latest2026-08-30 0856d32 3,523 BA view · diff
git:20260830.2b6336a2026-08-30 2b6336a 2,856 BA view · diff
git:20260712.9c135fd2026-07-12 9c135fd 310 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (3523 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

sandbaseai/sandbase-harness · 669 stars · license Apache-2.0 · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uajv2cb3cbtpze2z
GET https://markdownregistry.com/api/v1/resolve?ref=sandbaseai/sandbase-harness/code-review
GET https://markdownregistry.com/api/v1/blob/89c3d015f74599d5d04a74daefb19d4942f5cf34e598d2446f6ac4cda04ae927

Your agent 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.

More from sandbaseai/sandbase-harness

AGENTS.md agents
sandbaseai/sandbase-harness · AGENTS.md
git:20260920.3a66055 · audit A · 669 stars
llms.txt llmstxt
sandbaseai/sandbase-harness · llms.txt
git:20260831.53518ca · audit B · 669 stars

Every file in sandbaseai/sandbase-harness

Other files named code-review

code-review skill
github/awesome-copilot · .github/skills/code-review/SKILL.md · Review pull requests for repository fit, meaningful value, trustworthy provenance, differentiation, and maintainability…
git:20260923.d7e4ad9 · audit A · 39,368 stars
code-review skill
kyegomez/swarms · examples/single_agent/capabilities/skills/code-review/SKILL.md · Perform comprehensive code reviews focusing on best practices, security vulnerabilities, performance optimization, and…
git:20260707.2e41657 · audit A · 7,201 stars
code-review skill
thinkinaixyz/deepchat · resources/skills/code-review/SKILL.md · Comprehensive code review assistant that analyzes code quality, security, and best practices
git:20260113.8fd50e4 · audit A · 6,342 stars
code-review skill
basicmachines-co/basic-memory · .agents/skills/code-review/SKILL.md · Use when reviewing Basic Machines code for house style, architecture risk, pre-merge hardening, or whether a change…
git:20260609.03ba268 · audit A · 4,028 stars
code-review skill
a5c-ai/babysitter · library/methodologies/bmad-method/skills/code-review/SKILL.md
git:20260601.da7723a · audit C · 1,809 stars
code-review skill
a5c-ai/babysitter · library/methodologies/rpikit/skills/code-review/SKILL.md · Structured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts…
git:20260601.da7723a · audit A · 1,809 stars
code-review skill
block/berd · .agents/skills/code-review/SKILL.md · Senior engineer code review focused on catching issues before they become PR comments. Reviews only changed lines…
git:20260812.9b88cac · audit A · 936 stars
code-review skill
jackyst0/awesome-agent-skills · examples/code-review/SKILL.md · Smart code review skill that helps review code quality, identify potential issues, and provide improvement suggestions.
git:20260128.ad055be · audit A · 643 stars

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