spec-tasks

spec-tasks is a command for coding agents from gotalab/cc-sdd. It costs 6 tokens per session (654 once invoked), scanned A, original, MIT.

A command that creates a step-by-step implementation task list from a completed feature design. It can generate new tasks or merge with an existing task file, with optional automatic approval and sequential ordering.

In plain words
What is it for?
Use it after the design phase to prepare implementation tasks for a feature specification.
Why use it?
It breaks a design into concrete work items and helps identify which tasks can be handled in parallel.

Command

About the project

cc-sdd is a spec-driven development workflow for coding agents: it turns approved software specifications into requirements, designs, task plans, and extended autonomous implementation. Developers use it across several AI coding agents, with independent review and task-level continuation for long-running work. The catalogue entries provide commands, skills, agents, and instructions for using this workflow.

gotalab/cc-sdd · 3,646 stars · on GitHub

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/gotalab/cc-sdd/spec-tasks
Clone the repo
git clone --depth 1 https://github.com/gotalab/cc-sdd

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 spec-tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/gotalab/cc-sdd/spec-tasks.svg)](https://agentmods.dev/commands/gotalab/cc-sdd/spec-tasks)
Your own site
<a href="https://agentmods.dev/commands/gotalab/cc-sdd/spec-tasks"><img src="https://agentmods.dev/badge/commands/gotalab/cc-sdd/spec-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 654 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 $0.00006 $0.00654
Opus 5 $0.00003 $0.00327
Sonnet 5 $0.00001 $0.00131
Haiku 4.5 $0.00001 $0.00065

Measured 5d ago against content hash 3484f78143fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

tools/cc-sdd/templates/agents/claude-code-agent/commands/spec-tasks.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Tasks Generator

Parse Arguments

  • Feature name: $1
  • Auto-approve flag: $2 (optional, "-y")
  • Sequential mode flag: $3 (optional, "--sequential")

Validate

Check that design has been completed:

  • Verify {{KIRO_DIR}}/specs/$1/ exists
  • Verify {{KIRO_DIR}}/specs/$1/design.md exists
  • Determine sequential = ($3 == "--sequential")

If validation fails, inform user to complete design phase first.

Invoke Subagent

Delegate task generation to spec-tasks-agent:

Use the Task tool to invoke the Subagent with file path patterns:

Task(
  subagent_type="spec-tasks-agent",
  description="Generate implementation tasks",
  prompt="""
Feature: $1
Spec directory: {{KIRO_DIR}}/specs/$1/
Auto-approve: {true if $2 == "-y", else false}
Sequential mode: {true if sequential else false}

File patterns to read:
- {{KIRO_DIR}}/specs/$1/*.{json,md}
- {{KIRO_DIR}}/steering/*.md
- {{KIRO_DIR}}/settings/rules/tasks-generation.md
- {{KIRO_DIR}}/settings/rules/tasks-parallel-analysis.md (include only when sequential mode is false)
- {{KIRO_DIR}}/settings/templates/specs/tasks.md

Mode: {generate or merge based on tasks.md existence}
Instruction highlights:
- Map all requirements to tasks and list requirement IDs only (comma-separated) without extra narration
- Promote single actionable sub-tasks to major tasks and keep container summaries concise
- Apply `(P)` markers only when parallel criteria met (omit in sequential mode)
- Mark optional acceptance-criteria-focused test coverage subtasks with `- [ ]*` only when deferrable post-MVP
"""
)

Display Result

Show Subagent summary to user, then provide next step guidance:

Next Phase: Implementation

Before Starting Implementation:

  • IMPORTANT: Clear conversation history and free up context before running /kiro:spec-impl
  • This applies when starting first task OR switching between tasks
  • Fresh context ensures clean state and proper task focus

If Tasks Approved:

  • Execute specific task: /kiro:spec-impl $1 1.1 (recommended: clear context between each task)
  • Execute multiple tasks: /kiro:spec-impl $1 1.1,1.2 (use cautiously, clear context between tasks)
  • Without arguments: /kiro:spec-impl $1 (executes all pending tasks - NOT recommended due to context bloat)

Read the full file on GitHub · 76 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. 5d ago First seen · 76 lines · 6 tokens per session scan A 3484f78143fc

Subscribe to this mod's changes

spec-tasks is a command published in the GitHub repository gotalab/cc-sdd (3,646 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 654 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.

Related

Other commands, from other repositories

evaluate

Evaluate a skill across model tiers using blind testing.

ai-plugin-marketplace/template · 11 tokens

ai-feature-eval-harness

Design an evaluation plan for a product AI feature (LLM- or model-backed output): measurable success criteria, a held-out labeled eval dataset shape, per-criterion grading (code-based first, then LLM-based for nuanced judgment), and a pass threshold, then persist as AIEVALPLAN.md. Use when the task ships or changes a…

Mozurok/fhorja.dev · 205 tokens

api-contract-review

Review an API contract (endpoints, request/response shapes, error codes, auth model) BEFORE implementation for naming consistency, versioning, pagination, idempotency, and alignment with existing endpoints. Distinct from review-hard (post-implementation risk) and repo-consistency-sweep (pattern matching on written…

Mozurok/fhorja.dev · 100 tokens

api-runtime-verify

Verify an implemented backend HTTP surface at runtime: per route, record the request actually made, the HTTP status, the response content-type, and the observed body shape, assert each response against the slice's acceptance behavior, classify the findings, and decide a PASS/FAIL/BLOCKED runtime gate. The probe's real…

Mozurok/fhorja.dev · 216 tokens

app-runtime-verify

Verify a built mobile or app runtime at runtime: run the app (device, emulator, or headless), read the captured runtime output (native logcat, iOS device log, or the Metro/JS console), classify any runtime errors against a per-stack taxonomy, and decide a PASS/FAIL runtime gate for the slice's acceptance behavior. The…

Mozurok/fhorja.dev · 227 tokens

apply-sweep-triage

Persist the user's triage decisions (apply, decline, discuss) from a SWEEP snapshot into REVIEWPREFERENCES.md so future sweeps suppress declined findings and track applied fixes. Use after the user has edited the triage values in a SWEEP snapshot file produced by repo-consistency-sweep. Do not use when no sweep…

Mozurok/fhorja.dev · 87 tokens