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.
npx agentmods add commands/restarter/lets-workflow/review-roundgit clone --depth 1 https://github.com/restarter/lets-workflowWhat 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 | $0.00066 | $0.01614 |
| Opus 5 | $0.00033 | $0.00807 |
| Sonnet 5 | $0.00013 | $0.00323 |
| Haiku 4.5 | $0.00007 | $0.00161 |
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.
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.
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.
- 2d ago First seen · 113 lines · 66 tokens per session scan A 46280c74bbca
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.