review-round

A command for processing a received set of review comments on a specification, document, or pull request (PR). It records decisions first, keeps the document unchanged during review, and applies the agreed edits in one final pass.

In plain words
What is it for?
Use it to triage inline comments, review files, or PR discussion threads, track each decision, and then incorporate all accepted changes.
Why use it?
Editing after every comment can create inconsistent changes when later decisions affect earlier ones. This workflow keeps the review organized and the artifact stable until decisions are complete.

Command

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.

agentmods
npx agentmods add commands/restarter/lets-workflow/review-round
Clone the repo
git clone --depth 1 https://github.com/restarter/lets-workflow
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.01614
Opus 5 $0.00033 $0.00807
Sonnet 5 $0.00013 $0.00323
Haiku 4.5 $0.00007 $0.00161

Measured 2d ago against content hash 46280c74bbca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-round 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 2d 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.

plugins/lets/commands/review-round.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Round - Work Through a Received Review

The inverse of /lets:review (which GENERATES findings): this CONSUMES a received review and incorporates it.

Core discipline: decisions go into the TASK as you go; the artifact stays FROZEN; all file edits happen in ONE pass at the very end. Never edit per-decision - cascading reframes change earlier items, and a half-edited spec mid-round is inconsistent.

IMPORTANT: If the spec below invokes any deferred tool (e.g. AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.

When to use

  • A reviewer (team lead / Principal / external) returns your spec/doc/PR with many comments (<!-- REVIEW ... -->, // REVIEW, threaded PR comments, a separate review .md).
  • A multi-item round where decisions interact / cascade.
  • NOT for: a single comment (just fix it); generating a review (/lets:review); a single GitHub PR thread (/lets:github-pr --respond).

Usage

/lets:review-round <path-or-source>     # annotated copy / review file / PR id
/lets:review-round                      # infer from context (last shared artifact)

Step 0: Locate & index the review

See the whole shape BEFORE deciding anything.

grep -rn '<!-- REVIEW' <review-dir>/*.md                 # inline markers
for f in <review-dir>/*.md; do printf "%s %s\n" "$f" "$(grep -c '<!-- REVIEW' "$f")"; done

Record total + per-file breakdown. Note ALL sources - a round often spans an inline copy AND a PR thread.

Step 1: Confirm the active task

Use the detect-task skill: Skill(skill: "lets:detect-task"). Every resolution lands on this task. If none, ask which task owns the artifact.

Step 2: Cluster into themes + surface REFRAMES first

  • Group the N comments into themes (by concern), not file order.
  • Flag reframe comments - ones that question a PREMISE (topology, mechanism, scope), not a detail. Decide these FIRST: they cascade and can moot/alter the nits.
  • Present the themed map to the user before triaging.

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 66 tokens per session scan A 46280c74bbca

Subscribe to this mod's changes

review-round is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 66 tokens to every session and 1,614 once invoked, about $0.0003 per session on Opus 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 2026-08-30.