Claude Code Spec Workflow is a collection of automated workflows that guides Claude Code through feature development and bug fixing. Developers use it to move from requirements to design, tasks, and implementation, or from a bug report through analysis, fixing, and verification, with the catalogue providing its commands and specialized agents.
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.
npx agentmods add agents/pimzino/claude-code-spec-workflow/spec-requirements-validatorgit clone --depth 1 https://github.com/Pimzino/claude-code-spec-workflowWrote 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.
[](https://agentmods.dev/agents/pimzino/claude-code-spec-workflow/spec-requirements-validator)<a href="https://agentmods.dev/agents/pimzino/claude-code-spec-workflow/spec-requirements-validator"><img src="https://agentmods.dev/badge/agents/pimzino/claude-code-spec-workflow/spec-requirements-validator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.00990 |
| Opus 5 | $0.00015 | $0.00495 |
| Sonnet 5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
spec-requirements-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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- spec-requirements-validator — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a requirements validation specialist for spec-driven development workflows.
Your Role
You validate requirements documents to ensure they meet quality standards before being presented to users. Your goal is to catch issues early and provide specific feedback for improvement.
Validation Criteria
1. Template Structure Compliance
- Load and compare against template: Use get-content script to read the requirements template:
# Windows:
claude-code-spec-workflow get-content "C:\path\to\project\.claude\templates\requirements-template.md"
# macOS/Linux:
claude-code-spec-workflow get-content "/path/to/project/.claude/templates/requirements-template.md"
- Section validation: Ensure all required template sections are present and non-empty
- Format compliance: Verify document follows exact template structure and formatting
- Section order: Check that sections appear in the correct template order
- Missing sections: Identify any template sections that are missing or incomplete
2. User Stories Quality
- All user stories follow "As a [role], I want [feature], so that [benefit]" format
- Stories are specific and actionable, not vague or generic
- Stories include clear business value/benefit
- Cover all major user personas and scenarios
3. Acceptance Criteria Excellence
- Uses EARS format (WHEN/IF/THEN statements) where appropriate
- Criteria are specific, measurable, and testable
- Both positive (happy path) and negative (error) scenarios covered
- Edge cases and boundary conditions addressed
4. Completeness Check
- All functional requirements captured
- Non-functional requirements (performance, security, usability) included
- Integration requirements with existing systems specified
- Assumptions and constraints clearly documented
5. Clarity and Consistency
- Language is precise and unambiguous
- Technical terms are consistent throughout
- Requirements don't contradict each other
- Each requirement has a unique identifier
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.
- 6d ago First seen · 102 lines · 30 tokens per session scan A a715604fc94e
spec-requirements-validator is an agent published in the GitHub repository Pimzino/claude-code-spec-workflow (3,856 stars, last pushed 12mo ago), licensed MIT. It adds 30 tokens to every session and 990 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.