compare-specs

compare-specs is a command for Claude Code from fabriqaai/specs.md. It costs 0 tokens per session (1,232 once invoked), scanned A, original, MIT.

A command for comparing written software specifications with the code that implements them.

In plain words
What is it for?
Checking a feature, agent, or whole system in either direction: finding spec requirements absent from code or implementation details absent from the specs.
Why use it?
It reveals missing work, mismatches, and code that was added without being documented.

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/fabriqaai/specs.md/compare-specs
Clone the repo
git clone --depth 1 https://github.com/fabriqaai/specs.md

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 compare-specs

README.md
[![agentmods](https://agentmods.dev/badge/commands/fabriqaai/specs.md/compare-specs.svg)](https://agentmods.dev/commands/fabriqaai/specs.md/compare-specs)
Your own site
<a href="https://agentmods.dev/commands/fabriqaai/specs.md/compare-specs"><img src="https://agentmods.dev/badge/commands/fabriqaai/specs.md/compare-specs.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 1,232 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 $0.01232
Opus 5 $0.00000 $0.00616
Sonnet 5 $0.00000 $0.00246
Haiku 4.5 $0.00000 $0.00123

Measured 5d ago against content hash ba5a8471a85f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare-specs 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.

.claude/commands/compare-specs.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compare Specs and Implementation

Command: /compare-specs

Compare specifications in memory-bank/ with their corresponding implementations in src/ to identify gaps, inconsistencies, and missing items.


Comparison Modes

Choose a comparison mode based on what you want to analyze:

Mode 1: Spec → Implementation (Default)

Find what's documented in specs but missing or inconsistent in implementation.

  • Identifies incomplete implementations
  • Finds mismatches between spec requirements and actual code

Mode 2: Implementation → Spec

Find what's implemented but not documented in specs.

  • Identifies undocumented features
  • Finds implementation details that should be in specs

Process

Step 1: Identify Scope

Ask the user:

What would you like to compare?

  1. Specific agent (e.g., inception-agent, construction-agent, master-agent)
  2. Specific feature (e.g., bolt planning, story creation, estimation)
  3. Full system (compare all specs vs all implementations)

Direction:

  • A) Spec → Implementation (find missing implementations)
  • B) Implementation → Spec (find missing documentation)
  • C) Both directions

Step 2: Locate Files

Spec locations (memory-bank/):

memory-bank/
├── intents/
│   ├── 001-multi-agent-orchestration/
│   │   └── units/
│   │       ├── master-agent/unit-brief.md
│   │       ├── inception-agent/unit-brief.md
│   │       ├── construction-agent/unit-brief.md
│   │       └── operations-agent/unit-brief.md
│   ├── 002-agentic-coding-tool-integration/
│   └── 003-memory-bank-system/
├── standards/
│   ├── coding-standards.md
│   ├── tech-stack.md
│   └── system-architecture.md
├── research/
│   └── (research documentation)
├── glossary.md
└── term-mappings.md

Implementation locations (src/flows/aidlc/):

src/flows/aidlc/
├── agents/
│   ├── master-agent.md
│   ├── inception-agent.md
│   ├── construction-agent.md
│   └── operations-agent.md
├── commands/
├── .specsmd/
│   ├── skills/
│   │   ├── master/
│   │   ├── inception/
│   │   └── construction/
│   ├── templates/
│   └── memory-bank.yaml

Read the full file on GitHub · 204 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 · 204 lines · 0 tokens per session scan A ba5a8471a85f

Subscribe to this mod's changes

compare-specs is a command published in the GitHub repository fabriqaai/specs.md (206 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,232 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 2026-08-30.