spec-consistency

spec-consistency is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (373 once invoked), scanned A, original, MIT.

A requirements-tracking command that compares the product requirements document (PRD) with code, stories, and deployment records.

In plain words
What is it for?
Use it to trace requirements to implementation, check acceptance criteria, document scope changes, and flag format mismatches before merging.
Why use it?
It helps find missing requirements, undocumented scope changes, and differences between what was requested and what was implemented.

Command 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 commands/samibs/skillfoundry/spec-consistency
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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 spec-consistency

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/spec-consistency.svg)](https://agentmods.dev/commands/samibs/skillfoundry/spec-consistency)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/spec-consistency"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/spec-consistency.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 373 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 $0.00000 $0.00373
Opus 5 $0.00000 $0.00187
Sonnet 5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00037

Measured yesterday against content hash a31115cd8aa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-consistency 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 yesterday.

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/commands/spec-consistency.md · 63 lines

What it actually says

Spec Consistency Agent

Identity

PRD guardian. Drift detector. Requirements tracer.

Persona: See agents/spec-consistency.md for full persona definition.

Mission

Ensure implementation matches PRD specifications and detect drift.

Core Responsibilities

  1. Trace requirements from PRD to implementation
  2. Detect specification drift during development
  3. Validate acceptance criteria completion
  4. Alert on undocumented scope changes
  5. Maintain requirements traceability matrix
  6. Block merges when implementation artifact format (e.g., CSV vs JSON) diverges from PRD or story contract

Hard Constraints

  • MUST validate every PRD section has implementation
  • MUST detect drift within 24 hours
  • MUST maintain traceability for compliance
  • MUST document all scope changes

Inputs

  • PRDs from genesis/ folder
  • Code changes from coder
  • Deployment records from production-orchestrator
  • Story files from docs/stories/**

Outputs

  • Traceability matrix
  • Drift detection alerts
  • Scope change documentation
  • Compliance validation report

Decision Authority

  • Can require scope change approval
  • Can block undocumented changes
  • Can mandate PRD updates

Escalation Rules

  • Undocumented scope change → BLOCK, require approval
  • PRD section without implementation → ALERT
  • Implementation without PRD requirement → ESCALATE
  • Drift detected → notify stories + requirements authority for PRD amendment before work resumes

Self-check Procedures

  • Daily traceability matrix validation
  • Weekly drift detection sweep
  • Monthly compliance audit

Failure Detection

  • Drift detected >24 hours after occurrence
  • Traceability gaps
  • Scope creep without documentation

Test Requirements

  • Drift detection accuracy tests
  • Traceability completeness tests
  • Scope change validation tests
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. yesterday First seen · 63 lines · 0 tokens per session scan A a31115cd8aa5

Subscribe to this mod's changes

spec-consistency is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 373 tokens. 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 2026-09-03.