tests

A test-planning workflow that reads a software design and creates unit tests for individual parts and integration tests for parts working together. It writes tests before the implementation is built.

In plain words
What is it for?
Use it to plan tests for modules, services, adapters, data handling, and other parts described in an architecture document, including tests for a selected feature part.
Why use it?
It turns the design into specific checks, so important behavior is agreed on before coding begins. Tests can expose missing or unclear design decisions early.

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/andkirby/markdown-ticket/tests
Clone the repo
git clone --depth 1 https://github.com/andkirby/markdown-ticket
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,607 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00000 $0.01607
Opus 5 $0.00000 $0.00804
Sonnet 5 $0.00000 $0.00321
Haiku 4.5 $0.00000 $0.00161

Measured 2d ago against content hash 239662b1ed84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tests 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.

prompts/mdt/commands/tests.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Test Specification Workflow (v8)

Generate unit/integration tests from architecture design. Tests written AFTER architecture, BEFORE implementation.

Skill Discovery

Check AGENTS.md for skills matching this workflow. If found, invoke via Skill tool before proceeding.

Decision Tree

Input: /mdt:tests {CR-KEY} [--prep] [--part X.Y]

Is architecture.md present?
├─ No → ERROR: Run /mdt:architecture first
│
└─ Yes → What mode?
    ├─ --prep flag → Prep mode (GREEN tests, lock behavior)
    │   └─ Read: prep/architecture.md
    │   └─ Output: prep/tests.md
    │
    └─ Feature mode → RED tests (fail until implemented)
        ├─ Multi-part (part-*/ folders exist)?
        │   ├─ --part specified → Use that part
        │   └─ Multiple parts → Prompt for selection
        │
        └─ Output: [part-X.Y/]tests.md + test files

Extraction: What to Test

From architecture.md, extract three categories:

1. Module Interfaces (methods/functions)

Architecture Element Test Type
Component/Module Unit: public interface
Service Integration: dependencies
Adapter Integration: external systems

2. Data Mechanisms (CRITICAL - often missed)

Scan architecture for concrete data rules that need explicit tests:

Pattern Example Required Tests
Boundary "max 100 items", "limit N" At N-1, N, N+1
Format "UUID", "email", "ISO date" Valid accepted, invalid rejected
Config env vars, config files Present, missing, malformed
State "when empty", "when full" Each state transition

3. External Dependency Tests

For each external dependency declared in architecture (env var, CLI tool, API, service), require at least one real integration test (not mocked). If a real dependency is unavailable in CI, use a local stub or contract test and explicitly note the limitation.

Dependency Type Required Test
Env var Behavior when var is set vs absent (real env)
External command At least one test with a real command (e.g., echo test)
API/Service At least one test against real or local endpoint (or contract test if gated)

Read the full file on GitHub · 218 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. 2d ago First seen · 218 lines · 0 tokens per session scan A 239662b1ed84

Subscribe to this mod's changes

tests is a command published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,607 tokens. 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 2026-08-31.