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/dwarvesf/dwarves-kit/test-plan-review-teamgit 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/test-plan-review-team)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/test-plan-review-team"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/test-plan-review-team.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.02961 |
| Opus 5 | $0.00030 | $0.01481 |
| Sonnet 5 | $0.00012 | $0.00592 |
| Haiku 4.5 | $0.00006 | $0.00296 |
Grade A, and why
test-plan-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 yesterday.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a test-design critique coordinator. Your job is to stress-test a spec's TEST PLAN from 6 angles in parallel, tighten it through a bounded revise loop, and report a verdict. This mirrors /kit:devs-team (which critiques the solution design) and /kit:review-team (which critiques code), at the test-design altitude: it critiques the ## Test plan AFTER /kit:test-plan writes it and BEFORE /kit:execute runs it. It is an opt-in lane, report-only; it never blocks /kit:execute.
Why this lane exists: the spec gets adversarial review (/kit:spec-validate) and the code gets it (/kit:review-team), but the test design , the bridge between them , was authored once and executed unreviewed. The quality bar (docs/verification/test-design-standard.md) existed only as reference. This lane is its executor.
Process
Bracket the phase for timing (SPEC-129) before starting: bash lib/gate/gate-ledger.sh outcome <rid> test-plan start.
Step 1: Find the test plan to critique
Read the ## Test plan, spec-first: resolve the active docs/specs/SPEC-NNN-<slug>.md the way /kit:next does (branch-aware, SPEC-005); if several specs match, ask the user which one, do not auto-pick. /kit:execute resolves the active spec through this SAME path, so the plan you critique is the one execute will read.
Read that spec's ## Test plan section, plus its ## Acceptance Criteria (or per-task acceptance checkboxes) and any named failure modes / risks (the lenses need both the plan and what it is supposed to cover). If the spec has no ## Test plan, say so, tell the user to run /kit:test-plan first, and stop. Do not invent a test plan to critique.
Note the spec; you will write the critique back to that same spec.
Step 2: Dispatch 6 lenses in parallel
Dispatch these 6 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 spec's ## Test plan text, its ## Acceptance Criteria, and the named failure modes.
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.
- yesterday First seen · 109 lines · 59 tokens per session scan A 23c1b085235c
test-plan-review-team is a command published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 2,961 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 2026-09-04.
Other commands, from other repositories
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
OPSX: Archive
Archive a completed change in the experimental workflow.
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
OPSX: Sync
Sync delta specs from a change to main specs.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Update
Update a change - revise existing planning artifacts and keep them coherent (Experimental).