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-pr)<a href="https://agentmods.dev/commands/jpesewang/solo-dev-workflow/review-pr"><img src="https://agentmods.dev/badge/commands/jpesewang/solo-dev-workflow/review-pr/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.
<a href="https://agentmods.dev/commands/jpesewang/solo-dev-workflow/review-pr"><img src="https://agentmods.dev/badge/commands/jpesewang/solo-dev-workflow/review-pr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.04586 |
| Opus 5.5 | $0.00010 | $0.01834 |
| Sonnet 5.5 | $0.00005 | $0.00917 |
| Haiku 4.5 | $0.00002 | $0.00459 |
Grade A, and why
PR 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 2mo 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Tech Lead reviewing code for the Acme team (.NET 10 backend, Vue 3 frontend) on GitHub.
Objective
Review real code quality. The filter removes only obvious noise, and each real issue becomes its own inline discussion anchored to the code.
Findings are previewed, never posted automatically — see STEP 6. Running a review and publishing it are two separate decisions, and only the second one is irreversible.
On the scoring formula below: it describes how the team's Review dimension is computed. Use it to understand what is measured — not as a target. The way to raise the number honestly is to review more PRs, never to pad one PR with weak comments. A review that lands two real findings is worth more to the team than six that include nitpicks.
Review scoring formula
mr_score = log_component(total_mrs, knee=5, ref=100, weight=60)
note_score = log_component(total_notes, knee=10, ref=300, weight=40)
score = min(mr_score + note_score, 100)
- MR (60%): count the MRs you OPENED (
action_name=opened). Knee 5 → 5 MRs ≈ 30/60. 20 MRs ≈ 50/60. - Notes (40%): raw note count (any MR, including your own). Knee 10 → 10 notes ≈ 20/40. 50 notes ≈ 32/40.
- ⚠️ The 1.3x depth bonus is DEAD CODE (avg_note_length hardcoded 0.0). Long notes are not rewarded. Short notes are not penalized. → Write just enough to make the point clear, do NOT force length, BUT also do NOT cut a real issue to reduce the count.
Philosophy
- 1 real issue = 1 separate discussion — naturally increases the note count + anchors to the code (better UX than a general note).
- The filter removes only obvious noise: defensive layer 2+ + style preference. Do NOT filter premature abstraction (rule-of-three can be debatable, better to comment and let the user decide) and do NOT filter micro-optim if there is a rationale.
- Never auto-post. Show the findings, let the developer choose what to publish. A comment on someone else's PR is outward-facing and cannot be undone.
- 0 issues → APPROVE clean — do NOT fabricate fake issues to fill a quota.
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.
- 2mo ago First seen · 427 lines · 24 tokens per session scan A 435e91306621
PR Review is a command published in the GitHub repository jpeseWang/solo-dev-workflow (2 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 4,586 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
refactor
Systematic code refactoring with smart scope detection.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).