Borrowing it
Nothing to install: this file belongs to blackpaw-studio/leo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/blackpaw-studio/leo/main/.claude/commands/review-next.mdgit clone --depth 1 https://github.com/blackpaw-studio/leoWrote 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/blackpaw-studio/leo/review-next)<a href="https://agentmods.dev/commands/blackpaw-studio/leo/review-next"><img src="https://agentmods.dev/badge/commands/blackpaw-studio/leo/review-next/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/blackpaw-studio/leo/review-next"><img src="https://agentmods.dev/badge/commands/blackpaw-studio/leo/review-next.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 | $0.00032 | $0.02022 |
| Opus 5.5 | $0.00013 | $0.00809 |
| Sonnet 5.5 | $0.00006 | $0.00404 |
| Haiku 4.5 | $0.00003 | $0.00202 |
Grade A, and why
review-next 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-next — one iteration of the Leo kanban review loop
You are the reviewer agent. A separate builder agent runs /work-next. Your job starts when a PR is open and a card sits in In Review.
Like /work-next, this is one iteration. A human wraps it in /loop Nm /review-next. Do not loop inside this command.
Prerequisites
ghCLI authenticated withproject+reposcopes- Write access to
blackpaw-studio/leo - Branch protection on
maineither off, or the token is in an allow list
Run and sanity-check:
gh auth status
gh repo view blackpaw-studio/leo --json defaultBranchRef
Constants
- Project number:
3 - Project owner:
blackpaw-studio(org) - Repo:
blackpaw-studio/leo - Merge strategy: squash
- CI must be: green (all required checks passed)
- Review state file:
~/.leo/state/review-next-cursor.json— tracks the last reviewed HEAD sha per PR to avoid re-reviewing an unchanged PR
Gather the queue
- Pull project items where Status =
In Review:gh project item-list 3 --owner blackpaw-studio --format json --limit 50 - For each item, follow the linked PR. If the item has no open PR, log it and skip.
- Sort PRs by
updated_atascending (oldest first — fairness).
If the queue is empty: print no PRs to review and exit 0.
Pick one PR
Take the oldest. Call it $PR. Capture:
- PR number, head sha, base branch, head branch
- title, body
- linked issue number (from
Closes #Nin body or the card link) - mergeable state, mergeStateStatus
- file list + diff (
gh pr diff $PR --repo blackpaw-studio/leo) - CI status:
gh pr checks $PR --repo blackpaw-studio/leo --json - existing reviews and review comments
State machine — exactly one branch executes
1. PR is a draft
Skip. Move on to the next PR. If none left, exit.
2. PR has label agent-skip or do-not-merge
Skip.
3. PR is not mergeable (conflicts)
Attempt a merge of origin/main into the PR branch:
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 · 219 lines · 32 tokens per session scan A 19cabb6eebde
review-next is a command published in the GitHub repository blackpaw-studio/leo (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,022 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
code-review
Review the current branch changes for bugs and style issues.
align
Context-aware alignment. In plan mode it audits the active plan and folds the amendments in. Otherwise it reviews the branch, a named branch, or a pull request against Ion's principles, authors a fix plan, and after approval implements and commits the fixes.
resolve-dependabot-prs
Triage open Dependabot PRs, return a quick risk/action summary table, then enter planning mode with an ordered rebase→merge→follow-up→resume resolution plan.
review
Review current changes for correctness, style, and potential issues.
iterate
Work in iterations with implementation rounds followed by critical review passes.
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.