auto-review.skeleton

auto-review.skeleton is a command for coding agents from varienos/agentic-workflow. It costs 0 tokens per session (3,038 once invoked), scanned A, original, MIT.

An automatic review loop for Git changes. It remembers the last reviewed change, reviews new differences, fixes minor findings, and creates backlog tasks for major findings.

In plain words
What is it for?
Use it to review the latest commit, a named commit, or a commit range, detect whether new meaningful changes exist, apply minor fixes, and record major issues as backlog tasks.
Why use it?
It avoids repeatedly reviewing the same change and separates small corrections from issues that need planned work.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/varienos/agentic-workflow/auto-review.skeleton
Clone the repo
git clone --depth 1 https://github.com/varienos/agentic-workflow

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for auto-review.skeleton

README.md
[![agentmods](https://agentmods.dev/badge/commands/varienos/agentic-workflow/auto-review.skeleton.svg)](https://agentmods.dev/commands/varienos/agentic-workflow/auto-review.skeleton)
Your own site
<a href="https://agentmods.dev/commands/varienos/agentic-workflow/auto-review.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/auto-review.skeleton.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,038 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03038
Opus 5 $0.00000 $0.01519
Sonnet 5 $0.00000 $0.00608
Haiku 4.5 $0.00000 $0.00304

Measured 4d ago against content hash 89af3759f30d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-review.skeleton scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Agentbase/templates/core/commands/auto-review.skeleton.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Review - Loop Uyumlu Diff Review

Son review hash'ini izler, yeni diff varsa shallow review yapar, MINOR bulgulari dogrudan duzeltir, MAJOR bulgular icin backlog task acar. Kullanim: /auto-review, /auto-review <commit_hash>, /auto-review HEAD~3..HEAD



Step 1 - Diff ve State Tespiti

1.1 - Arguman Cozumleme

Girdi Davranis
Bos Son commit: cd ../Codebase && git diff HEAD~1..HEAD
Commit hash Belirtilen commit: cd ../Codebase && git show <hash>
Range Aralik: cd ../Codebase && git diff <range>

1.2 - Normalize Diff Cikar

Review edilecek diff'i deterministik sekilde cikar:

cd ../Codebase && git diff --no-ext-diff --minimal <range_veya_default>

Bu diff'ten su bilgileri cikar:

  • Degisen dosya listesi
  • Eklenen/silinen satir sayilari
  • Degisiklik tipi (fix, refactor, test, config)

KURAL: Diff bossa veya sadece whitespace degisikligi varsa "Incelenecek yeni degisiklik yok" deyip DUR.

1.3 - Hash Hesapla

Diff hash'ini stabil sekilde hesapla:

CURRENT_DIFF_HASH=$(cd ../Codebase && git diff --no-ext-diff --minimal <range_veya_default> | shasum -a 256 | awk '{print $1}')
CURRENT_HEAD=$(cd ../Codebase && git rev-parse HEAD)

1.4 - State Dosyasini Yukle

.claude/tracking/auto-review-state.json dosyasini kullan:

{
  "last_reviewed_hash": null,
  "last_review_target": null,
  "last_reviewed_head": null,
  "last_reviewed_at": null,
  "last_fix_commit": null,
  "last_report_path": null
}

Read the full file on GitHub · 296 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 296 lines · 0 tokens per session scan A 89af3759f30d

Subscribe to this mod's changes

auto-review.skeleton is a command published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,038 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.