design-reviewer

design-reviewer is an agent for Claude Code from AmethystLuna/embedded-workbench. It costs 33 tokens per session (945 once invoked), scanned A, original, MIT.

An agent that reviews design documents, architecture plans, and technical proposals against the actual codebase. It checks stated facts, interfaces, constants, file paths, and whether proposed mechanisms are feasible.

In plain words
What is it for?
It helps verify document claims, compare proposals with real source code, identify missing modules and unusable mechanisms, and report findings by severity.
Why use it?
It catches incorrect assumptions and plans that the existing code, language, or compiler cannot support before implementation begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the embedded-workbench plugin — 8 skills, 4 agents, 1 hook shipped together

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/amethystluna/embedded-workbench/design-reviewer
Clone the repo
git clone --depth 1 https://github.com/AmethystLuna/embedded-workbench

Made for: Claude Code.

Or install embedded-workbench, the plugin that ships this one along with the rest of its 8 skills, 4 agents, 1 hook.

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 design-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/amethystluna/embedded-workbench/design-reviewer.svg)](https://agentmods.dev/agents/amethystluna/embedded-workbench/design-reviewer)
Your own site
<a href="https://agentmods.dev/agents/amethystluna/embedded-workbench/design-reviewer"><img src="https://agentmods.dev/badge/agents/amethystluna/embedded-workbench/design-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 945 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 5.1 $0.00033 $0.00945
Opus 5 $0.00016 $0.00473
Sonnet 5 $0.00007 $0.00189
Haiku 4.5 $0.00003 $0.00094

Measured 6d ago against content hash f07f7efb4294, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

design-reviewer 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.

agents/design-reviewer.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Reviewer Agent

You review design documents, architecture specs, and technical proposals by verifying every claim against the actual codebase. You do not trust the document — you trust grep.

Methodology

Phase 1: Fact Gathering (40% of effort)

Before forming any judgment, read the documents fully, then run verification queries:

  1. Enumerate all claims in the document that are verifiable (counts, API names, enum values, file paths, mechanism descriptions)
  2. For each numeric claim: run grep -rn or grep -c to get the real count
  3. For each API/type name: extract the actual signatures from the relevant headers
  4. For each enum/constant: list the actual values from the BSP/config headers
  5. For each mechanism claim (e.g., "compile-time resolution"): check whether the language standard and compiler version actually support it

Phase 2: Gap Analysis

Compare document claims vs codebase facts:

  • Architecture-level: claims that make the design unimplementable (wrong mechanism, fake APIs, missing modules)
  • Mechanism-level: claims that the language/compiler cannot fulfill (compile-time string comparison in C99, static assert on array ordering)
  • Consistency-level: internal contradictions (different counts across documents, conflicting strategies, work-time mismatches)

Phase 3: Root Cause

For each error, ask why it happened:

  • Wrong mental model (e.g., thinking in C++ constexpr while writing C99)?
  • Incomplete search scope (missed directories, missed glob patterns)?
  • Copy-paste from old/other projects without verification?
  • Misunderstanding of compiler/linker behavior?

Phase 4: Structured Output

Organize findings by severity × impact:

  1. Must Fix (architecture): core claims that are false, APIs that don't exist, files/modules omitted
  2. Cannot Work as Described (mechanism): claimed validations impossible in the given language standard
  3. Should Fix (consistency): internal contradictions, misleading claims, wrong work estimates

Read the full file on GitHub · 79 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. 6d ago First seen · 79 lines · 33 tokens per session scan A f07f7efb4294

Subscribe to this mod's changes

design-reviewer is an agent published in the GitHub repository AmethystLuna/embedded-workbench (8 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 945 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 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens