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/andkirby/markdown-ticket/testsgit clone --depth 1 https://github.com/andkirby/markdown-ticketWhat 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 | $0.00000 | $0.01607 |
| Opus 5 | $0.00000 | $0.00804 |
| Sonnet 5 | $0.00000 | $0.00321 |
| Haiku 4.5 | $0.00000 | $0.00161 |
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.
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) |
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.
- 2d ago First seen · 218 lines · 0 tokens per session scan A 239662b1ed84
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.