Home / tibursocampos / agent-dev-toolkit · GitHub

code-review SKILL.md skillA

code-review from tibursocampos/agent-dev-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add tibursocampos/agent-dev-toolkit/code-review@git:20261012.c159b3f

Pins git:20261012.c159b3f in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: tibursocampos/agent-dev-toolkit
Path: core/skills/code-review/SKILL.md
Versions recorded: 10
Latest version: git:20261012.c159b3f, committed Oct 12, 2026
First version recorded: Aug 2, 2026
Size: 23,670 bytes
Repository stars: 6
License: MIT

Review a branch or diff against PRD/PLAN and project standards. Asks single vs multi-angle when omitted. Use when reviewing a PR or invoking /code-review.

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

## STOP - Read before ANY tool call

1. Read `{{GUARDRAILS_PATH}}`
2. Read `_shared/sdd-artifacts/SESSION.md`; load session-state for `$Cwd`
3. If the relevant gate is not approved: **STOP** - ask user **(pt-BR)** - do **NOT** Write/Shell
4. SDD/develop skills: after **ONE** step/task, **STOP** session - handoff only
5. This skill body is **English**; user-facing prompts may be **(pt-BR)**

### Step -1 - Gate check (report in chat before continuing)

```
Gate check:
[ ] guardrails.mdc read
[ ] SESSION.md read; session-state loaded
[ ] PIPELINE.md read (SDD skills only)
[ ] User confirmed current action (sim)
-> If any unchecked: STOP
```

---

## Trigger
**Negative signal:** Do not activate this skill when the request lacks one of the positive signals below or its required context; topic similarity or an isolated keyword alone is insufficient.

Invoke when the user asks for: `/code-review`, `review this PR`, `code review`.

**Review mode (mandatory choice - no silent default):**

| Mode | Explicit invoke examples |
|------|--------------------------|
| **Single** | `single`, `single-angle`, `simples` |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add tibursocampos/agent-dev-toolkit/code-review@sha256:2c5ac52ccee5892e

The line at the top of this page pins the label git:20261012.c159b3f, 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](https://markdownregistry.com/badge/art_vn2jznfxpa2w6kyk.svg)](https://markdownregistry.com/a/art_vn2jznfxpa2w6kyk)

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

Versions

The registry has recorded 10 versions of this file, between Aug 2, 2026 and Oct 12, 2026, about one every 8 days.

version	committed	commit	size	audit
git:20261012.c159b3f latest	2026-10-12	c159b3f	23,670 B	A	view · diff
git:20261009.3afb93a	2026-10-09	3afb93a	23,375 B	A	view · diff
git:20261009.98ac682	2026-10-09	98ac682	14,097 B	A	view · diff
git:20261005.a294a9e	2026-10-05	a294a9e	13,770 B	A	view · diff
git:20261003.d75bf34	2026-10-03	d75bf34	13,449 B	A	view · diff
git:20260926.123e72f	2026-09-26	123e72f	13,127 B	A	view · diff
git:20260924.2d90fab	2026-09-24	2d90fab	12,765 B	A	view · diff
git:20260924.3ac55b1	2026-09-24	3ac55b1	11,998 B	A	view · diff
git:20260831.80517f1	2026-08-31	80517f1	11,001 B	A	view · diff
git:20260802.d4636a4	2026-08-02	d4636a4	12,637 B	A	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 (23670 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

tibursocampos/agent-dev-toolkit · 6 stars · license MIT · pushed 2026-10-21 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_vn2jznfxpa2w6kyk
GET https://markdownregistry.com/api/v1/resolve?ref=tibursocampos/agent-dev-toolkit/code-review
GET https://markdownregistry.com/api/v1/blob/2c5ac52ccee5892e4815e666f81bb9a7139c8ca1f8c194f6436747ac67f8252a

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.