tasks

A command that turns project plans into small implementation tasks with clear, checkable acceptance criteria. It also uses project rules and stored project notes when creating them.

In plain words
What is it for?
Use it to create tasks from all plans or from one plan file, regenerate tasks, or view a task summary.
Why use it?
It removes the need to break a broad plan into detailed work by hand. The checks help make each task specific and objectively verifiable.

Command for Claude Code

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/ddunnock/claude-plugins/tasks
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,446 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 $0.00008 $0.02446
Opus 5 $0.00004 $0.01223
Sonnet 5 $0.00002 $0.00489
Haiku 4.5 $0.00001 $0.00245

Measured 2d ago against content hash 0b5690d54b64, 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.

mcps/knowledge-mcp/.claude/commands/tasks.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tasks

Generate SMART-validated implementation tasks from plans + constitution + memory files.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).


Usage

/tasks                  # Generate tasks from all plans
/tasks plan.md          # Generate from specific plan
/tasks --all            # Force regenerate all tasks
/tasks --status         # Show task summary without generating

Memory Directives

Load these directive files for task generation:

Always loaded:

  • constitution.md - Global principles, section references for tasks
  • testing.md - Test coverage requirements (80% minimum)
  • git-cicd.md - Git workflow and CI/CD standards

Project-specific (detected: Python ≥3.11, Poetry, MCP SDK):

  • python.md - Python standards, Pyright strict, ruff linting
  • security.md - API key management, input validation

SMART Acceptance Criteria Validation

Every acceptance criterion must pass SMART validation:

Element Requirement Fail Condition
Specific Clear, concrete action "properly", "correctly", "fully", "appropriately"
Measurable Objective verification No command/metric/file check defined
Achievable Single task scope Requires other tasks to complete first
Relevant Ties to task purpose No trace to plan/requirement/ADR
Time-bound Immediate verification Requires external delays or human approval

SMART Strictness Level

Level Behavior When to Use
Strict Block until criterion rewritten Critical tasks, security-related
Standard Flag for review, allow with warning Default for most tasks
Relaxed Log finding only Exploratory/research tasks

Selected for this project: Standard

Criterion Format

**Acceptance Criteria**:
- [ ] File `src/knowledge_mcp/store/qdrant_store.py` exists
      Verification: `ls src/knowledge_mcp/store/qdrant_store.py`
      SMART: S✓ M✓ A✓ R✓ T✓
- [ ] QdrantStore class passes type checking
      Verification: `poetry run pyright src/knowledge_mcp/store/`
      SMART: S✓ M✓ A✓ R✓ T✓

Read the full file on GitHub · 380 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 · 380 lines · 8 tokens per session scan A 0b5690d54b64

Subscribe to this mod's changes

tasks is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 2,446 once invoked, about $0.0000 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 2026-08-30.