review-mine

review-mine is a command for Claude Code from jpeseWang/solo-dev-workflow. It costs 0 tokens per session (2,942 once invoked), scanned A, original, MIT.

A second-opinion review command for code changes that have not been committed yet. It examines the uncommitted changes from logic, design, and security-and-user-experience perspectives.

In plain words
What is it for?
Use it before committing to receive a findings list about the current code diff. It is separate from reviewing a pull request and from automated lint fixes.
Why use it?
It can expose problems before the changes are committed, without automatically changing the code or posting comments elsewhere.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Use it before committing to receive a findings list about the current code diff. It is separate from reviewing a pull request and from automated lint fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jpesewang/solo-dev-workflow/review-mine
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.

Clone the repo
git clone --depth 1 https://github.com/jpeseWang/solo-dev-workflow

Made for: Claude Code.

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 review-mine

README.md
[![agentmods](https://agentmods.dev/badge/commands/jpesewang/solo-dev-workflow/review-mine.svg)](https://agentmods.dev/commands/jpesewang/solo-dev-workflow/review-mine)
Your own site
<a href="https://agentmods.dev/commands/jpesewang/solo-dev-workflow/review-mine"><img src="https://agentmods.dev/badge/commands/jpesewang/solo-dev-workflow/review-mine.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 2,942 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.
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 $0.00000 $0.02942
Opus 5 $0.00000 $0.01471
Sonnet 5 $0.00000 $0.00588
Haiku 4.5 $0.00000 $0.00294

Measured 7d ago against content hash a4d059aed4f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

review-mine 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 7d 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.

variants/team-jira/commands/review-mine.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Tech Lead reviewing uncommitted code for the $PROJECT_NAME project. Review from 3 independent perspectives (Logic / Design / Security+UX). The output is a findings list for the user to decide what to fix.

Objective

Give the user a second opinion on the code they just wrote, before /commit. No auto-fix. No gate. Just recommendations.

Difference from /commit STEP 2

Aspect /commit STEP 2/6 /review-mine
Goal Lint + auto-fix surface Deep critique, fresh eyes
Agents 1 (self-review) 3 parallel (Logic/Design/UX)
Output Gate pass/fail Findings list
Auto-fix Yes (safe ones) NEVER — only recommend
Speed Fast Slower (~30-60s, parallel)

Difference from /review-pr

Aspect /review-pr /review-mine
When After the MR is created BEFORE committing
Scope The whole MR Uncommitted diff (default)
Post Jira/GitLab May post a note Does NOT post anywhere

Philosophy

  • Anti-noise: do NOT report the 4 useless groups (per [[feedback_review_pr_anti_noise]]):
    • Defensive coding (try-catch when unnecessary, null check on an internal parameter)
    • Premature abstraction (extract a helper for 1 use site, "in case we need it later")
    • Micro-optim (useMemo for a primitive, useCallback that isn't needed)
    • Style nitpicks (semicolon, quote style, trailing comma — Prettier handles it)
  • Self-review bias awareness: the AI is reviewing code the AI wrote → easy to miss issues. Bias mitigation: 3 agents with different prompts, an anti-noise filter, prioritizing concrete bugs over vague suggestions.
  • Concrete > vague: "Line 42 null pointer when user.profile=null" is GOOD; "Consider error handling" is BAD.

STEP 1: Determine scope

Parse the argument:

Arg Scope
(none) uncommitted diff (git diff + git diff --staged + untracked files content)
staged only staged (git diff --staged)
HEAD~N the N most recent commits on the current branch (git diff HEAD~N..HEAD)
<sha>..<sha> a specific range

Read the full file on GitHub · 278 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. 7d ago First seen · 278 lines · 0 tokens per session scan A a4d059aed4f9

Subscribe to this mod's changes

review-mine is a command published in the GitHub repository jpeseWang/solo-dev-workflow (2 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,942 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 2026-08-31.