speckit.tasks

speckit.tasks is a command for Claude Code from pilotspace/pilot-space. It costs 18 tokens per session (1,072 once invoked), scanned A, original, Apache-2.0.

A command that creates a dependency-ordered task list for a software feature from its design documents.

In plain words
What is it for?
It helps generate tasks from technical plans, prioritized user stories, data models, API contracts, research, and test scenarios.
Why use it?
It turns plans and requirements into an actionable implementation checklist and uses only the project documents that are available.

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/pilotspace/pilot-space/speckit.tasks
Clone the repo
git clone --depth 1 https://github.com/pilotspace/pilot-space

Made for: Claude Code.

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 speckit.tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/pilotspace/pilot-space/speckit.tasks.svg)](https://agentmods.dev/commands/pilotspace/pilot-space/speckit.tasks)
Your own site
<a href="https://agentmods.dev/commands/pilotspace/pilot-space/speckit.tasks"><img src="https://agentmods.dev/badge/commands/pilotspace/pilot-space/speckit.tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,072 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 $0.00018 $0.01072
Opus 5 $0.00009 $0.00536
Sonnet 5 $0.00004 $0.00214
Haiku 4.5 $0.00002 $0.00107

Measured 3d ago against content hash 684473080f1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.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 3d 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.

.claude/commands/speckit.tasks.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Consider user input before proceeding (if not empty). Load @docs/dev-pattern/README.md to understand project rules.

Workflow

1. Setup

Run from repo root:

.specify/scripts/bash/check-prerequisites.sh --json

Parse FEATURE_DIR and AVAILABLE_DOCS from output. Use absolute paths throughout.

For arguments with single quotes (e.g., "I'm Groot"), use: 'I'\''m Groot' or "I'm Groot"

2. Load Design Documents

Read from FEATURE_DIR:

Document Required Contains
plan.md Yes Tech stack, libraries, structure
spec.md Yes User stories with priorities (P1, P2, P3)
data-model.md No Entities to map to user stories
contracts/ No API endpoints to map to user stories
research.md No Decisions for setup tasks
quickstart.md No Test scenarios

Generate tasks based on available documents only.

3. Generate Tasks

  1. Extract tech stack and structure from plan.md
  2. Extract prioritized user stories from spec.md
  3. For each optional doc that exists:
    • data-model.md: Map entities to user stories
    • contracts/: Map endpoints to user stories
    • research.md: Extract decisions for setup tasks
  4. Generate tasks organized by user story (see Task Format below)
  5. Create dependency graph showing story completion order
  6. Identify parallel execution opportunities per user story
  7. Validate: each user story has complete tasks and is independently testable

4. Write tasks.md

Use .specify/templates/tasks-template.md as structure template.

Required sections:

  • Feature name from plan.md
  • Phase 1: Setup (project initialization)
  • Phase 2: Foundational (blocking prerequisites for all user stories)
  • Phase 3+: One phase per user story in priority order
  • Final Phase: Polish & cross-cutting concerns

Each user story phase includes:

  • Story goal and independent test criteria
  • Tests (only if requested in spec)
  • Implementation tasks with file paths

Read the full file on GitHub · 150 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. 3d ago First seen · 150 lines · 18 tokens per session scan A 684473080f1a

Subscribe to this mod's changes

speckit.tasks is a command published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,072 once invoked, about $0.0001 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 2026-08-31.