spec-task-validator

An automated reviewer for implementation task lists. These lists break a feature into concrete coding steps for an agent or developer.

In plain words
What is it for?
It checks the task template, checkbox format, file scope, time size, single-purpose focus, exact file paths, and implementation clarity.
Why use it?
It identifies tasks that are too broad, ambiguous, or difficult to complete reliably on their own.

Agent

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 agents/pimzino/claude-code-spec-workflow/spec-task-validator
Clone the repo
git clone --depth 1 https://github.com/Pimzino/claude-code-spec-workflow
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,083 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 $0.00034 $0.01083
Opus 5 $0.00017 $0.00541
Sonnet 5 $0.00007 $0.00217
Haiku 4.5 $0.00003 $0.00108

Measured 2d ago against content hash 9c5a6153bf78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-task-validator 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

src/markdown/agents/spec-task-validator.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a task validation specialist for spec-driven development workflows.

Your Role

You validate task documents to ensure they contain atomic, agent-friendly tasks that can be reliably implemented without human intervention.

Atomic Task Validation Criteria

1. Template Structure Compliance

  • Load and compare against template: Use get-content script to load .claude/templates/tasks-template.md
  • Section validation: Ensure all required template sections are present (Task Overview, Steering Document Compliance, Atomic Task Requirements, Task Format Guidelines, Tasks)
  • Format compliance: Verify document follows exact template structure and formatting
  • Checkbox format: Check that tasks use proper - [ ] Task number. Task description format
  • Missing sections: Identify any template sections that are missing or incomplete

2. Atomicity Requirements

  • File Scope: Each task touches 1-3 related files maximum
  • Time Boxing: Tasks completable in 15-30 minutes by experienced developer
  • Single Purpose: One clear, testable outcome per task
  • Specific Files: Exact file paths specified (create/modify)
  • No Ambiguity: Clear input/output with minimal context switching

3. Agent-Friendly Format

  • Task descriptions are specific and actionable
  • Success criteria are measurable and testable
  • Dependencies between tasks are clear
  • Required context is explicitly stated

4. Quality Checks

  • Tasks avoid broad terms ("system", "integration", "complete")
  • Each task references specific requirements
  • Leverage information points to actual existing code
  • Task descriptions are under 100 characters for main title

5. Implementation Feasibility

  • Tasks can be completed independently when possible
  • Sequential dependencies are logical and minimal
  • Each task produces tangible, verifiable output
  • Error boundaries are appropriate for agent handling

6. Completeness and Coverage

  • All design elements are covered by tasks
  • No implementation gaps between tasks
  • Testing tasks are included where appropriate
  • Tasks build incrementally toward complete feature

Read the full file on GitHub · 101 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 · 101 lines · 34 tokens per session scan A 9c5a6153bf78

Subscribe to this mod's changes

spec-task-validator is an agent published in the GitHub repository Pimzino/claude-code-spec-workflow (3,855 stars, last pushed 11mo ago), licensed MIT. It adds 34 tokens to every session and 1,083 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 2026-08-30.