Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dwarvesf/dwarves-kitnpx agentmods add commands/dwarvesf/dwarves-kit/review-teamWrote 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/dwarvesf/dwarves-kit/review-team)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/review-team"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/review-team/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/dwarvesf/dwarves-kit/review-team"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/review-team.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 | $0.00049 | $0.06032 |
| Opus 5.5 | $0.00020 | $0.02413 |
| Sonnet 5.5 | $0.00010 | $0.01206 |
| Haiku 4.5 | $0.00005 | $0.00603 |
Grade A, and why
review-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a review coordinator. Your job is to dispatch 3 focused lenses in parallel, collect their findings, deduplicate, and present a unified report.
Prerequisites
- There are code changes to review (git diff is not empty)
- Optionally,
docs/specs/SPEC-NNN-<slug>.mdexists for spec-compliance checking
If no changes exist, tell the user and stop.
Process
Bracket the review phase for timing before starting: bash lib/gate/gate-ledger.sh outcome "$rid" review start.
Step 1: Gather the diff
Run git diff main (or git diff HEAD~N if on main). Capture the diff and the list of changed files.
Fail fast BEFORE any dispatch. Confirm the fixed point resolves
(git rev-parse <fixed-point>) and the diff is non-empty. A bad ref or an empty diff
fails here with one line , never inside four parallel subagents.
Advisory coverage-delta signal (ADVISORY, never blocks). Before dispatching the lenses, run the coverage-delta gate and fold its one line into the test-coverage lens's input:
bash lib/gate/coverage-delta.sh check "$(git rev-parse --show-toplevel)" --rid "$(bash lib/gate/gate-ledger.sh rid 2>/dev/null)"
It prints one [coverage-delta] line , WARNING under-tested (source moved, no matching test
change; it names the uncovered files), ok (source + test moved together), or exempt
(docs/test/generated only). It ALWAYS exits 0 and records an advisory | GATE | coverage-delta | ran | marker on the ledger; it is a warn-only signal for the test-coverage reviewer, NOT a
block. This is the live dispatch path for the coverage-delta gate (the Review phase, off the push
blocker). A WARNING is advisory input to the test-coverage lens, never a stop.
Step 2: Dispatch 3 lenses in parallel
Dispatch these 3 subagents via the Task tool. They can run simultaneously since they're all read-only and don't modify anything.
Domain lens (opt-in). In addition to the fixed 3, classify the changed files' domain , bash lib/classify/role-classify.sh classify "<changed paths + diff summary>" , and if a domain REVIEWER exists for that domain (kit:performance-reviewer, kit:api-reviewer, kit:frontend-reviewer, kit:infra-reviewer), dispatch it too, in the same parallel batch, through its domain lens. This is the live dispatch path for the read-only domain reviewers (workers dispatch via the /kit:execute builder lookup instead). Skip when no domain reviewer matches; the fixed 3 lenses are unchanged.
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.
- 3d ago Changed · +2 lines e21b697731be
- 21d ago Changed d910c2cb6d87
- 1mo ago Changed · +4 tokens per session cfa72ee278a7
- 1mo ago Changed c1359efe84dc
- 1mo ago Changed a629e5e12585
- 1mo ago Changed · +6 lines 59b441167fea
- 1mo ago First seen · 368 lines · 45 tokens per session scan A dcd012a82fc6
review-team is a command published in the GitHub repository dwarvesf/dwarves-kit (12 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 6,032 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
impl-review
John Carmack-level implementation review via Codex, Copilot, Cursor, Claude or a host reviewer.
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
review
Run /review — see .claude/commands/review.md for the authoritative spec.
pr-feedback-ingest
Turn PR feedback (Greptile, CI, bots, humans) into a traceable backlog, so the next step is a narrow implement-approved-slice. Corrective scope only. Use when a PR has review feedback to map to files and slices. Do not use for a new direction or contract (use post-review-pivot), no payload, or task-memory drift only…
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
post-review-pivot
Capture what a PR or team review changed about the intended approach, separate keep from revert, and update task memory. Does not implement product code. Use when review changes direction (wrong fields or migrations) or a pivot digest is needed. Do not use for corrective feedback (use pr-feedback-ingest), when there…