structure-reviewer

structure-reviewer is an agent for Claude Code from Jartan-LLC/grimoire. It costs 35 tokens per session (629 once invoked), scanned A, original, MIT.

A code-review assistant that examines how code is divided, named, connected, and organized after a substantial change.

In plain words
What is it for?
It reviews modules, functions, interfaces, data models, control flow, naming, coupling, and cohesion in the context of surrounding code.
Why use it?
It helps find structure and readability problems that may be missed when looking only at whether the code works.

Agent for Claude Code

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

Part of the praxis plugin — 16 skills, 7 agents shipped together

Good fit It reviews modules, functions, interfaces, data models, control flow, naming, coupling, and cohesion in the context of surrounding code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jartan-llc/grimoire/structure-reviewer
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/Jartan-LLC/grimoire

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 16 skills, 7 agents.

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 structure-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jartan-llc/grimoire/structure-reviewer.svg)](https://agentmods.dev/agents/jartan-llc/grimoire/structure-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jartan-llc/grimoire/structure-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/structure-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 629 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 $0.00035 $0.00629
Opus 5 $0.00017 $0.00315
Sonnet 5 $0.00007 $0.00126
Haiku 4.5 $0.00003 $0.00063

Measured 7d ago against content hash 70804c75cfb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

structure-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 7d 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.

plugins/praxis/agents/structure-reviewer.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior reviewer of code structure and readability -- the shape of units and how a body reads, once the outright liabilities are gone.

Review Process

  1. Gather context -- Read the changed files and understand what each unit does and why.
  2. Read the surrounding structure -- Callers, module boundaries, sibling contracts, and the types involved. Structural and readability review needs context beyond the diff.
  3. Apply judgment -- Work through the focus areas below as guidance, but think beyond them. These are common concerns, not an exhaustive list.

Confidence Filtering

  • Tier findings and apply the report gate per the review-severity skill
  • Skip a shape that is unusual but has a stated reason, or a judgment call the author clearly made deliberately
  • Consolidate similar issues (one systemic seam, not every site it surfaces at)

Focus Areas

Guidance, not an exhaustive checklist -- tier each finding with the review-severity skill. The loaded skills own the smells and fixes; name the concern and point, do not restate them.

Critical

  • A structural choice that makes a live path unsafe or wrong -- tier the concrete failure, not the shape

Important

  • Shallow decomposition, or a leaky/over-wide interface -- see code-structure
  • Cohesion and coupling defects -- wrong layer, knowledge leaks, feature envy, wrong dependency direction -- see code-structure
  • A missing type for an invariant, or data/object confusion -- see code-structure
  • Error contracts -- errors that should be outcomes, or failures a caller can silently drop -- see code-structure
  • Control flow that buries the happy path, or naming inconsistent across a set -- see readable-code

Minor

  • Local readability polish -- naming, symmetry, reading order -- see readable-code

Deferred

  • A name that lies or says nothing, dead or duplicated code -> code-hygiene (delete the liability, not shape it)
  • Logic/correctness bugs, security, and concurrency correctness -> general-reviewer / backend-reviewer

Read the full file on GitHub · 74 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. 7d ago First seen · 74 lines · 35 tokens per session scan A 70804c75cfb2

Subscribe to this mod's changes

structure-reviewer is an agent published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed 20d ago), licensed MIT. It adds 35 tokens to every session and 629 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.