test-plan

test-plan is a command for coding agents from dwarvesf/dwarves-kit. It costs 44 tokens per session (3,603 once invoked), scanned A, original, MIT.

Derive a test-case coverage matrix from a spec's acceptance criteria before /kit:execute. Writes a ## Test plan section into the active spec. A coverage target across categories, not an exhaustive test list.

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/dwarvesf/dwarves-kit/test-plan
Clone the repo
git clone --depth 1 https://github.com/dwarvesf/dwarves-kit

Wrote 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.

agentmods badge for test-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/test-plan.svg)](https://agentmods.dev/commands/dwarvesf/dwarves-kit/test-plan)
Your own site
<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/test-plan"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/test-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00044 $0.03603
Opus 5 $0.00022 $0.01801
Sonnet 5 $0.00009 $0.00721
Haiku 4.5 $0.00004 $0.00360

Measured today against content hash 55cf6bb51fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-plan 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 today.

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.

commands/test-plan.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a test-plan author. Your job is to turn a spec's acceptance criteria into a test-case coverage matrix BEFORE /kit:execute, so the build has a planned coverage target instead of ad-hoc tests.

This is NOT a roundtable and has NO personas. Test planning derives from FIXED acceptance criteria, so the right shape is systematic coverage, not divergence. (A design critique explores an open space; this enumerates against a fixed contract.)

Process

Bracket the phase for timing (SPEC-129) before starting: bash lib/gate/gate-ledger.sh outcome <rid> test-plan start.

Step 0: No active spec, feature already live

If Step 1 finds no spec with acceptance criteria, and the feature under test already exists (no build planned), don't send the user to /kit:spec -- that command wants a feature idea to build, not a description of what already shipped. Instead:

  1. Dispatch kit:research-context on the target area with a one-line charter (what you're hunting for, per docs/impl-playbook/exploratory-testing.md's SBTM discipline, personal-scale: 15-30 min, no formal report).
  2. From its findings, write a minimal docs/specs/SPEC-NNN-<slug>.md: Status: DRAFT (reverse-engineered), and an ## Acceptance Criteria section describing the feature's ACTUAL observed behavior, checkbox per behavior. No other spec sections -- nothing is being planned here. If kit:research-context finds nothing observable, say so and do not write a stub with fabricated criteria.
  3. Continue to Step 1 against this stub, unchanged.

Step 1: Find the active spec

Detect the active docs/specs/SPEC-NNN-<slug>.md the way /kit:next does (branch-aware). If several specs match, ask the user which one. /kit:execute resolves the active spec through this SAME detection path, so the plan you write lands in the spec execute will read. Read its ## Acceptance Criteria section (or the per-task acceptance checkboxes). If no spec has acceptance criteria to read, say so and point the user to /kit:spec.

Read the full file on GitHub · 194 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. today First seen · 194 lines · 44 tokens per session scan A 55cf6bb51fc9

Subscribe to this mod's changes

test-plan is a command published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 3,603 once invoked, about $0.0002 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.