speckit-tasks

speckit-tasks is a skill for Claude Code from rafaelandrade74/spec-forge. It costs 35 tokens per session (2,015 once invoked), scanned A, original, MIT.

A workflow for generating an ordered list of implementation tasks from a feature's specification and design documents, stored in Spec-Forge.

In plain words
What is it for?
Use it to prepare coding, testing, setup, and other implementation tasks after planning is complete.
Why use it?
It breaks planned work into concrete tasks and records their dependencies in one place.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to prepare coding, testing, setup, and other implementation tasks after planning is complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rafaelandrade74/spec-forge/speckit-tasks
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.

Any agent
npx skills add rafaelandrade74/spec-forge --skill speckit-tasks
Clone the repo
git clone --depth 1 https://github.com/rafaelandrade74/spec-forge

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/skills/rafaelandrade74/spec-forge/speckit-tasks.svg)](https://agentmods.dev/skills/rafaelandrade74/spec-forge/speckit-tasks)
Your own site
<a href="https://agentmods.dev/skills/rafaelandrade74/spec-forge/speckit-tasks"><img src="https://agentmods.dev/badge/skills/rafaelandrade74/spec-forge/speckit-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,015 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.02015
Opus 5 $0.00017 $0.01007
Sonnet 5 $0.00007 $0.00403
Haiku 4.5 $0.00003 $0.00201

Measured 7d ago against content hash 7bb4cc0342dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

apps/cli/templates/speckit-tasks/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

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

Spec-Forge Setup (replaces setup-tasks.ps1)

  1. Read .specify/feature.json for spec_forge_feature_id. If missing, instruct the user to run /speckit-specify first and stop.
  2. Call get_feature_snapshot with { featureId }. This returns the current specification and plan in one call — the equivalent of "load plan.md" and "load spec.md" from FEATURE_DIR, plus the active constitution. There is no AVAILABLE_DOCS list to check: the plan's research/dataModel/contracts/quickstart fields are either present or empty arrays/omitted in the JSON — treat missing/empty the same way the original treated a missing optional file ("not all projects have all documents; generate tasks based on what's available").
    • Required: plan must exist and be at least in_review. If missing or still draft, instruct the user to run /speckit-plan first and stop.

Outline

  1. Execute task generation workflow:

    • From plan.content: extract tech stack, libraries, project structure (technicalContext), dataModel, contracts, research decisions (for setup tasks)
    • From specification.content: extract user stories/scenarios with their priorities (P1, P2, P3, etc. — infer priority order from the order they appear in userScenarios / acceptanceScenarios if not explicit)
    • If dataModel entries exist: map each entity to the user story(ies) that need it
    • If contracts entries exist: map each interface contract → the user story it serves
    • Generate tasks organized by user story (see Task Generation Rules below)
    • Generate a dependency graph showing user story completion order (encoded via each task's dependsOn array of task codes — see Checklist Format below)
    • Validate task completeness (each user story has all needed tasks, independently testable)
  2. Build the task list as an array of task objects, structured with:

    • Phase 1: Setup tasks (project initialization) — phase: "Setup", no story
    • Phase 2: Foundational tasks (blocking prerequisites for all user stories) — phase: "Foundational", no story
    • Phase 3+: One phase per user story (in priority order from the specification) — phase: "US<n>" (e.g. "Phase 3" or the story name), story: "US1" etc.
    • Final Phase: Polish & cross-cutting concerns — phase: "Polish", no story
    • Within each user-story phase: Tests (if requested) → Models → Services → Endpoints → Integration

Read the full file on GitHub · 155 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. 7d ago First seen · 155 lines · 35 tokens per session scan A 7bb4cc0342dc

Subscribe to this mod's changes

speckit-tasks is a skill published in the GitHub repository rafaelandrade74/spec-forge (0 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 2,015 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

task-generation

Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.

attilaszasz/sdd-pilot · 35 tokens

quality-assurance

Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.

attilaszasz/sdd-pilot · 36 tokens

instructions-management

Manages the project instructions — a document of non-negotiable project principles and governance rules. Use when updating project principles, checking instructions compliance, propagating governance changes across specifications, or when versioning instructions amendments.

attilaszasz/sdd-pilot · 46 tokens

sddp-amend

Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.

attilaszasz/sdd-pilot · 33 tokens

sddp-projectplan

Decompose the project into prioritized epics and execution waves. Direct command-bar dispatch only; do not select for general queries.

attilaszasz/sdd-pilot · 31 tokens

spec-driven-task-implementer

Use this skill when an approved Spec-Driven change has reached Phase 4 and the user wants a task, phase, or full feature implemented from .specs/changes/ . It executes tasks in order, updates task status immediately, verifies each task before completion, and should not be used before implementation approval.

lindoelio/spec-driven-steroids · 70 tokens