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.
git clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/devs-team)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/devs-team"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/devs-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/devs-team"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/devs-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 | $0.00041 | $0.01561 |
| Opus 5.5 | $0.00016 | $0.00624 |
| Sonnet 5.5 | $0.00008 | $0.00312 |
| Haiku 4.5 | $0.00004 | $0.00156 |
Grade A, and why
devs-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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a design-critique coordinator. Your job is to stress-test a solution DESIGN from 5 engineering angles in parallel, merge the findings, and report a verdict. This mirrors /kit:review-team (which critiques code) one altitude up: it critiques the design before the spec hardens. It is an opt-in lane, report-only; it never blocks /kit:spec.
Process
Bracket both phases this lane owns for timing: bash lib/gate/gate-ledger.sh outcome <rid> review start and bash lib/gate/gate-ledger.sh outcome <rid> design-critique start.
Step 1: Find the design to critique
Read the design's ## Solution, spec-first:
- The active
docs/specs/SPEC-NNN-<slug>.md's## Solutionsection IF a spec exists. Resolve the active spec the way/kit:nextdoes (branch-aware); if several specs match, ask the user which one, do not auto-pick. - ELSE
docs/briefs/DECISION-BRIEF-<slug>.md's## Solutionsection (falling back to the legacydocs/briefs/DECISION-BRIEF.md), the pre-spec window, before aSPEC-NNNexists.<slug>is the feature's kebab-case slug, the same one/kit:think//kit:designused for this feature's brief.
The spec is the carrier once it exists; the brief is the home only pre-spec (before /kit:spec). If neither has a ## Solution (no active spec with one, AND the brief is absent or has no ## Solution), say so, suggest the user run /kit:design or /kit:spec first, and stop. Do not invent a design to critique.
Note which doc holds the design; you will write the critique back to that same doc.
Step 2: Dispatch 5 lenses in parallel
Dispatch these 5 subagents via the Task tool in a single batch. They run simultaneously since they are all read-only and modify nothing. Pass each lens the design's ## Solution text and the relevant problem context.
Each lens returns 2-5 findings (each with a severity CRITICAL / HIGH / MEDIUM / LOW and a concrete fix) plus a 0-10 score for the design under that lens.
- Simplicity -- is this the least-machinery solution that solves the problem? Flag speculative features, premature abstraction, accidental complexity.
- Performance -- where does this design get slow or expensive at scale? Hot paths, N+1 patterns, unbounded growth, wasted work.
- Boundaries / composability -- are the units cleanly separated (one purpose, a defined interface, testable independently)? Flag leaky boundaries and tight coupling.
- Data-model & correctness -- is the data model sound? Flag invariants that can break, ambiguous states, race conditions, lost updates.
- Operability / failure-modes -- what happens when a dependency fails, times out, or returns garbage? Flag missing failure handling, silent failures, hard-to-debug paths.
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.
- 1mo ago Changed 1cfa639a0ea1
- 1mo ago Changed 410f04a02361
- 1mo ago First seen · 101 lines · 41 tokens per session scan A dcd1a81b4e50
devs-team is a command published in the GitHub repository dwarvesf/dwarves-kit (12 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,561 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…