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.
git clone --depth 1 https://github.com/jpeseWang/solo-dev-workflowWrote 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.
[](https://agentmods.dev/commands/jpesewang/solo-dev-workflow/review-mine)<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 7d ago First seen · 278 lines · 0 tokens per session scan A a4d059aed4f9
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.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.