review-capacity-check — Claude Code skill: review queue
review-capacity-check is a Claude Code skill that checks unfinished agent work before another launch. It runs before parallel batches and during weekly reviews.
MIT ★ 741 updated 2026-11-11
/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stackWhat review-capacity-check does
review-capacity-check inventories finished agent work that still waits for acceptance: open agent PRs, completed subagent outputs, and unchecked analyses. It records the stakes for each item, then produces a decision to launch, clear the queue first, or add an automatic check.
The skill inspects multi-agent pipelines as well. A later agent must have access to the original files, logs, or links instead of relying only on a hand-off summary, because caveats can disappear across several steps. The weekly review records tasks agents now perform and marks which ones should still be practiced by hand.
When more than a couple of high-stakes items are waiting, the next session is blocked. Review load can be reduced with tests, lint, or CI from taste-to-checks, and each result can include the evidence block from agent-brief.
What it helps with
- clear a queue of open agent PRs
- assess the stakes of finished subagent results
- turn recurring review work into automated checks
- verify that the final pipeline agent reads original sources
- track tasks the agents have taken over from the team
Example prompts for the agent
- Check the finished agent queue and decide whether to launch another parallel session.
- Inspect the research agent, writer, and reviewer chain to confirm the last agent reads the original files, logs, or links.
- Make the weekly list of tasks agents now handle and mark which ones still need occasional manual practice.
How to install review-capacity-check
1Plugin marketplace
/plugin marketplace add MiniMax-AI/mcode-stack/plugin install ronny@mcode-stackThis installs the whole ronny plugin with all its skills
2Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill review-capacity-check -a claude-code3Manually: put the files in place
~/.claude/skills/review-capacity-check/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/review-capacity-check/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill review-capacity-check -a codex2Manually: put the files in place
.agents/skills/review-capacity-check/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill review-capacity-check -a cursor2Manually: put the files in place
.cursor/skills/review-capacity-check/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MiniMax-AI/mcode-stack stacks/ronny/skills/review-capacity-check2Manually: put the files in place
.github/skills/review-capacity-check/SKILL.md1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill review-capacity-check -a gemini-cli2Platform CLI
gemini skills install https://github.com/MiniMax-AI/mcode-stack --path stacks/ronny/skills/review-capacity-checkManually: put the files in place
.devin/skills/review-capacity-check/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about review-capacity-check
How do I install review-capacity-check in Claude Code?
For the marketplace method, run /plugin marketplace add MiniMax-AI/mcode-stack, then run /plugin install ronny@mcode-stack. The installed skill is at ~/.claude/skills/review-capacity-check/SKILL.md.
What does review-capacity-check do?
It reviews unfinished agent work, records the stakes, and decides whether to launch another session, clear the queue, or add an automated check. It also checks that later agents in a pipeline can read the original sources.
When does review-capacity-check run?
It is used before another parallel session or subagent batch, after a day with many agent PRs, and during a weekly review.
Source text
SKILL.md · MIT
--- name: review-capacity-check description: Check whether finished agent work is piling up faster than we can stand behind it, and fix that by tightening automatic checks or running fewer parallel sessions instead of starting another one. Also checks that multi-agent chains read original sources, and which skills we are letting go. Use before launching another parallel session or subagent batch, at the end of a day with many agent PRs, or in a weekly review. --- # Review Capacity Check Running five MiniMax Code sessions in parallel is easy. Standing behind five results is not. Every agent we launch costs review time later. When finished work waits longer than it took to produce, we are not reviewing any more, we are hoping. ## 1. Count the queue Before starting another session, list what is already done but not yet accepted by us: open agent PRs, finished subagent outputs, analyses nobody has checked. For each, note the stakes (see `agent-brief`). If more than a couple of high-stakes items are waiting, do not launch. Clear the queue or reduce what needs us. ## 2. Reduce what needs us, not the bar In order of preference: 1. **Let checks do more**: add a test, lint or CI step so a class of review is automatic (see `taste-to-checks`). 2. **Make agents prove more**: require the evidence block from `agent-brief` in every result, so review starts from commands and output. 3. **Run fewer at once**: fewer sessions we can defend beat more we cannot. Skimming high-stakes work faster is not on the list. ## 3. Check the chain In a pipeline (research agent, then writer, then reviewer), each later agent should read the original source, not only the previous agent's summary. Summaries drop caveats; three hops later the caveat is gone and the claim is stronger than the data. Check that the last agent's context includes the source files, logs or links, not just the hand-off text. ## 4. Weekly: what are we no longer practicing? Write down one or two things the agent now always does for us (reading a stack trace, writing a migration, sizing a query). For each, decide on purpose: fine to let go, or keep doing it by hand now and then so we can still judge the agent's version. ## Output The queue with stakes, a decision (launch, clear first, or add a check), and the weekly list if it is that day. ## References - Addy Osmani, ["Critical thinking when agents do the work"](https://x.com/addyosmani/status/2117512471930167377)
© Ronny (MiniMax Code team) · MIT · MiniMax-AI/mcode-stack