auto-review

auto-review is a skill for Claude Code, Codex from WrongStack/WrongStack. It costs 67 tokens per session (1,774 once invoked), scanned A, original, MIT.

A setup and reference guide for an automatic code-review system that starts review agents whenever tracked files change during a coding session. It reports findings by severity and can trigger follow-up work for serious issues.

In plain words
What is it for?
Use it to configure or understand automatic reviews, review events and reports, choose providers or models, and control when serious findings trigger another agent.
Why use it?
It catches review issues during development instead of waiting until the end of a session. The automated reports help surface problems while the relevant changes are still fresh.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to configure or understand automatic reviews, review events and reports, choose providers or models, and control when serious findings trigger another agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wrongstack/wrongstack/auto-review
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.

Any agent
npx skills add WrongStack/WrongStack --skill auto-review
Clone the repo
git clone --depth 1 https://github.com/WrongStack/WrongStack

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/wrongstack/wrongstack/auto-review/github.svg)](https://agentmods.dev/skills/wrongstack/wrongstack/auto-review)
Your own site
<a href="https://agentmods.dev/skills/wrongstack/wrongstack/auto-review"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/auto-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auto-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/wrongstack/wrongstack/auto-review"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/auto-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00067 $0.01774
Opus 5.5 $0.00027 $0.00710
Sonnet 5.5 $0.00013 $0.00355
Haiku 4.5 $0.00007 $0.00177

Measured 5d ago against content hash 9ad36bb925d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-review 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 5d 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.

packages/core/skills/auto-review/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Review — Built-in Plugin

Selection card

  • Task: Operate the built-in automatic review plugin.
  • Start: Identify the scope and obtain an executable before-proof or review evidence.
  • Finish: apply the acceptance checks below; report observed results and unresolved constraints.

Overview

The wstack-auto-review plugin (built into @wrongstack/core) detects every git-tracked file change during a session and automatically dispatches a review subagent after a trailing file-quiet window. It extends the Chimera review pipeline with mid-session reviews while leaving any work still waiting at session.ended to the post-session Chimera path.

iteration.completed → git diff → trailing quiet window → chimera.review_needed event
                                                   ↓
                                    Director spawns review subagent
                                    (provider/model from config)
                                                  ↓
                                    Severity-ranked report → store + mailbox
                                                  ↓
                                    chimera.review_complete event
                                                  ↓
                                    chimera.report_available notification
                                                  ↓
                                    stop (with cascadeOn set: follow-up fix agents)

Status

This is a built-in plugin (packages/core/src/plugins/auto-review-plugin.ts), NOT a skill-based watcher. It is loaded automatically and enabled by default. Optional overrides in your config:

{
  "extensions": {
    "wstack-auto-review": {
      "provider": "deepseek",
      "model": "deepseek-chat",
      "fallbackProfile": "reliable",
      "modelSelection": "round-robin",
      "debounceMs": 15000,
      "maxFilesPerBatch": 15
    }
  }
}

Requirements

  • --director flag (Director mode) — the subagent spawning pipeline (execution.ts) requires the Director to be active. Without it, review events are silently skipped.
  • git available in the session working directory.

Read the full file on GitHub · 160 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. 5d ago Changed 9ad36bb925d9
  2. 6d ago Changed · +21 lines 1f3e7db9baf3
  3. 19d ago Changed · -1 lines 507a499cd238
  4. 29d ago Changed · -40 lines cc30685c25e1
  5. 1mo ago First seen · 180 lines · 67 tokens per session scan A bbf69307eda4

Subscribe to this mod's changes

auto-review is a skill published in the GitHub repository WrongStack/WrongStack (376 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,774 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

code-reviewer

Staff-engineer-level code review delivering 10 prioritized actionable findings across architecture, security, performance, and maintainability.

autohandai/code-cli · 26 tokens

pull-request-review

Review a pull request or branch diff like a staff engineer. Verify it does what the issue asks, find correctness and security defects with file and line evidence, check tests and compatibility, and deliver prioritized, actionable comments. Use for PR review, branch review, and "review my changes".

autohandai/code-cli · 61 tokens

verify

Answer "is this shippable / done?" with evidence before a commit or PR — fires on "verify", "is this done", "ready to ship?", pre-commit or pre-PR. Part of the Agentsmith harness; runs the project's verify phases and never claims "passing" without showing the output (R5).

PromptPartner/agentsmith · 69 tokens

meta-reviewing-ai-reviewing

AI integration review patterns. Use when reviewing model API calls, prompt construction, LLM output handling, RAG pipelines, and tool-calling code. Covers prompt-injection call-chain tracing, output validation, token budgets, retry/timeout handling, streaming, and key/PII exposure.

agents-inc/skills · 65 tokens

meta-reviewing-api-reviewing

Backend code review patterns. Use when reviewing API routes, database operations, auth middleware, and server utilities. Covers injection, boundary validation, authorization coverage, secret/PII exposure, error leakage, and query patterns.

agents-inc/skills · 50 tokens

meta-reviewing-infra-reviewing

Infrastructure code review patterns. Use when reviewing CI/CD workflows, Dockerfiles, deployment configs, and IaC. Covers supply-chain pinning, secret exposure, container hygiene, least-privilege permissions, and deployment safety.

agents-inc/skills · 52 tokens