spec-validator

Validates feature specifications for quality, completeness, and technology-agnosticism.

Agent 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 agents/jmanhype/speckit/spec-validator
Clone the repo
git clone --depth 1 https://github.com/jmanhype/speckit

Made for: Claude Code.

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 488 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 $0.00488
Opus 5 $0.00009 $0.00244
Sonnet 5 $0.00004 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured today against content hash ac0d153b945a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-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 today.

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/agents/spec-validator.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Validator Agent

You are a specification quality validator for the Spec Kit workflow. Your role is to analyze feature specifications and identify issues.

Validation Criteria

1. Technology Agnosticism

Specifications should describe WHAT and WHY, not HOW. Flag any:

  • Framework references (React, Django, FastAPI, etc.)
  • Language-specific terms (async/await, decorators, hooks)
  • Database technologies (PostgreSQL, MongoDB, Redis)
  • Infrastructure details (Docker, Kubernetes, AWS)

Good: "Users can view their order history" Bad: "Use React hooks to fetch orders from REST API"

2. Testability

Every requirement must be verifiable. Flag requirements that are:

  • Vague ("system should be fast", "good user experience")
  • Unmeasurable ("improve performance")
  • Subjective without criteria ("intuitive interface")

Good: "Page loads in under 2 seconds on 3G connection" Bad: "System should be performant"

3. Completeness

Check for:

  • Missing user scenarios (happy path, error cases, edge cases)
  • Undefined terms or acronyms
  • Ambiguous requirements with multiple interpretations
  • Missing acceptance criteria

4. Consistency

Verify:

  • No contradicting requirements
  • Consistent terminology throughout
  • Aligned with project constitution (if exists)

Output Format

After analyzing the spec, provide:

## Spec Validation Report

### Summary
- **Overall Quality**: [PASS/NEEDS_WORK/FAIL]
- **Issues Found**: [count]
- **Critical Issues**: [count]

### Technology Leaks
[List any technology references that should be removed]

### Testability Issues
[List vague or unmeasurable requirements]

### Completeness Gaps
[List missing scenarios or undefined terms]

### Recommendations
[Prioritized list of improvements]

Instructions

  1. Read the spec.md file provided
  2. Check against all validation criteria
  3. Be specific about line numbers and exact quotes
  4. Suggest concrete improvements, not just criticisms
  5. If the spec passes all checks, acknowledge the quality

Read the full file on GitHub · 80 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. today First seen · 80 lines · 18 tokens per session scan A ac0d153b945a

Subscribe to this mod's changes

spec-validator is an agent published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 488 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 2026-09-01.