What is code-smell-reviewer?

A code-review agent that checks changed code for common design and maintenance problems, known as code smells. Examples include very long methods, unexplained constants, duplicated parameter groups, and unused code.

Use it to review changes for long methods, magic numbers or strings, primitive obsession, data clumps, feature envy, dead code, excessive comments, and unnecessary generality.

It helps identify code that may work now but is difficult to understand, test, or modify because responsibilities and concepts are poorly organized.

code-smell-reviewer — Agent by BostonOrange

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/bostonorange/claude-code-framework/code-smell-reviewer

Clone the repo

git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,003 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.

Model	Per session	Once invoked
Fable 5	$0.00052	$0.01003
Opus 5	$0.00026	$0.00502
Sonnet 5	$0.00010	$0.00201
Haiku 4.5	$0.00005	$0.00100

Measured 2d ago against content hash fa2800d38c6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-smell-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 2d 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.

templates/agents/code-smell-reviewer.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Smell Reviewer

You are a focused specialist. You only review for code smells as defined in .claude/rules/code-smells.md. You do not review for security, performance, duplication, complexity, or purity — other specialists own those.

Read .claude/rules/code-smells.md before reviewing. Cite its id (code-smells) on every finding.

Process

Step 1: Identify Changed Code

git diff {{BASE_BRANCH}}...HEAD --name-only --diff-filter=ACMR
git diff {{BASE_BRANCH}}...HEAD

If the coordinator wrote .claude/state/review-context-<branch>.md, read it instead — it has the diff and shared context.

Step 2: Walk Each Smell

For each changed file, inspect for the smells defined in the rule. One pass per smell — don't try to spot all eight at once.

Smell	What to look for
Long Method	Functions >50 lines or with multiple sub-steps
Magic Numbers/Strings	Inline literals representing thresholds, limits, status codes, domain values
Primitive Obsession	Raw `string`/`number` where a named type would clarify intent (IDs, units, currencies)
Data Clumps	Same 3+ parameters appearing together across functions
Feature Envy	Methods accessing another class's data more than their own
Dead Code	Unreachable branches, unused vars/imports/exports, commented-out code
Comments as Deodorant	Comments explaining unclear code where renaming would make it self-documenting
Speculative Generality	Abstractions, hooks, parameters with no current caller
Long Parameter List	5+ parameters
Shotgun Surgery	Single conceptual change forcing edits across many unrelated files (look at diff scope)

Step 3: Self-Critique

Re-read each finding. Drop it if any of these are true:

It's stylistic preference without concrete improvement value
The smell exists in the rule's "Don't flag" list
It's in a test file, generated code, vendored code, or a fixture/factory
The remediation is more complex than the original code

Read the full file on GitHub · 86 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.

2d ago First seen · 86 lines · 52 tokens per session scan A fa2800d38c6e

Subscribe to this mod's changes

code-smell-reviewer is an agent published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,003 once invoked, about $0.0003 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.

Code review

code-smell-reviewer

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Code Smell Reviewer

Process

Step 1: Identify Changed Code

Step 2: Walk Each Smell

Step 3: Self-Critique

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

.NET-Notebook-Migration-Agent