review-design-verify

review-design-verify is a command for Claude Code from axiomantic/spellbook. It costs 17 tokens per session (616 once invoked), scanned A, original, MIT.

A review procedure for checking whether a design document matches the actual source code and can be implemented without guesswork. It marks each interface as verified or assumed, then simulates the implementation to expose unanswered questions.

In plain words
What is it for?
Use it to verify interfaces, compare documentation with source and examples, and find details that must be specified before coding.
Why use it?
It prevents developers from inventing parameters, return values, or behavior based only on names or incomplete documentation. This reduces implementation errors and debugging loops.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to verify interfaces, compare documentation with source and examples, and find details that must be specified before coding.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/review-design-verify
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.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

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 review-design-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/review-design-verify/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/review-design-verify)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/review-design-verify"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-design-verify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-design-verify

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/review-design-verify"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-design-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00017 $0.00616
Opus 5 $0.00009 $0.00308
Sonnet 5 $0.00003 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured 5d ago against content hash 7230722efd64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-design-verify 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.

commands/review-design-verify.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 4: Interface Verification

Invariant Principles

  1. Read source before accepting any interface claim — Assumed behavior from method names is the root cause of fabrication loops
  2. Every interface must be marked VERIFIED or ASSUMED — No unmarked entries; the distinction drives risk assessment
  3. Usage examples trump documentation — When docs and actual usage diverge, actual usage is ground truth. If neither exists: examine tests.

Fabrication Anti-Pattern

Wrong Right
Assume from name Read docstring, source
Code fails -> invent parameter Find usage examples
Keep inventing Write from VERIFIED behavior

Verification Table

Interface Verified/Assumed Source Read Notes

Factchecker Escalation

Trigger: security, performance, concurrency, numeric, or external-reference claims

Format: **Escalate:** [claim] | Loc: [X] | Category: [Y] | Depth: SHALLOW/MEDIUM/DEEP


Phase 5: Implementation Simulation

### Component: [name]
**Implement now?** YES/NO
**Questions:** [list]
**Must invent:** [what] - should specify: [why]
**Must guess:** [shape] - should specify: [why]

Read the full file on GitHub · 69 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 · 69 lines · 17 tokens per session scan A 7230722efd64

Subscribe to this mod's changes

review-design-verify is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 616 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 2026-09-03.