tasks

A planning command that turns an architecture document, test plan, and optional behavior-driven development notes into implementation tasks. Behavior-driven development describes software behavior through concrete examples and scenarios.

In plain words
What is it for?
Use it after the architecture and tests are prepared to create tasks for a feature or preparation phase, including separate parts of a larger change.
Why use it?
It keeps the task list tied to the agreed design and tests, while recording boundaries, exclusions, and duplicate-work risks.

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/tasks
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 4,372 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 $0.04372
Opus 5 $0.00000 $0.02186
Sonnet 5 $0.00000 $0.00874
Haiku 4.5 $0.00000 $0.00437

Measured 2d ago against content hash 694ab0f2e7bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tasks 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/tasks.md · 420 lines

How it starts

The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Task Breakdown Workflow (v11)

Generate tasks from architecture + tests + bdd. Tasks include constraints (scope boundaries, exclusions, anti-duplication), not just actions.

Decision Tree

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

Prerequisites exist?
├─ No architecture.md → ERROR: Run /mdt:architecture first
├─ No tests.md → ERROR: Run /mdt:tests first
│
├─ bdd.md exists? → Load as supplementary input (for E2E-only files)
│
└─ Yes → What mode?
    ├─ --prep → Read prep/architecture.md + prep/tests.md [+ prep/bdd.md]
    │   └─ Output: prep/tasks.md
    │
    └─ Feature → Read architecture.md + [part-X.Y/]tests.md [+ bdd.md]
        ├─ Multi-part? Prompt for part selection
        └─ Output: [part-X.Y/]tasks.md

Skill Discovery (MANDATORY)

Before generating tasks, discover project-required skills:

  1. Find all AGENTS.md files in the project (root + subdirectories, exclude .git/).
  2. Parse skill requirements: look for "Required Skills" tables, "MUST use skill" directives, or "load skill:" instructions.
  3. Map skills to directories: each skill applies to a package or directory scope (e.g., svelte5-best-practicespackages/frontend/).
  4. Assign skills to tasks: when a task's Creates/Modifies files fall within a skill's directory scope, add that skill to the task's **Skills** field.

If no AGENTS.md files exist, skip this step — no **Skills** field is written.

Task Template (Essential)

### Task {N}: {Brief description}

**Skills**: {skill-1}, {skill-2}  ← omit if no skills required for this task

**Milestone**: M{X} — {milestone name} (BR-X.Y)  ← omit if no bdd.md

**Structure**: `{path from architecture}`

**Makes GREEN (unit)**: *(from tests.md)*
- `test_file`: `test name`

**Makes GREEN (BDD)**: *(only on milestone's final task)*
- `scenario_name` → `e2e_test_file` (BR-X.Y)

**Enables (BDD)**: *(tasks that contribute to a future milestone)*
- `scenario_name` (BR-X.Y) — needs Task {M} to complete

**Scope**: {what this task owns}
**Boundary**: {what it must not touch}

**Creates**:
- {new file/module}

**Modifies**:
- {existing file/module}

**Must Not Touch**:
- {module/file outside task ownership}

**Create/Move**:
- {specific item 1}
- {specific item 2}

**Exclude**: {what NOT to include}

**Anti-duplication**: Import `{X}` from `{path}` — do NOT copy

**Duplication Guard**:
- Check owner module for target behavior before coding
- If logic exists elsewhere, add explicit merge/refactor task immediately (no parallel path)
- Verify no second runtime owner was introduced

**Verify**:
```bash
{test_command} --filter="..."   # unit tests GREEN
{e2e_command} --grep="..."      # BDD GREEN (only if Makes GREEN (BDD) present)

Done when:

  • Unit tests GREEN (were RED)
  • BDD scenarios GREEN (if Makes GREEN (BDD) listed)
  • No duplicated logic
  • Smoke test passes (feature works with real execution)
  • Fallback/absence paths match requirements (if applicable)

Read the full file on GitHub · 420 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 · 420 lines · 0 tokens per session scan A 694ab0f2e7bd

Subscribe to this mod's changes

tasks 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 4,372 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.