purity-reviewer

purity-reviewer is an agent for Claude Code from BostonOrange/claude-code-framework. It costs 48 tokens per session (1,409 once invoked), scanned A, original, MIT.

A code reviewer that checks whether business logic is predictable and separated from side effects such as database calls, network requests, file access, logging, or hidden state.

In plain words
What is it for?
Use it to review changed functions and classes for impure logic, input mutation, hidden state reads, query-command mixing, and single-responsibility problems.
Why use it?
It makes code easier to test and reuse by identifying mixed responsibilities, unexpected state changes, and non-deterministic behavior.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review changed functions and classes for impure logic, input mutation, hidden state reads, query-command mixing, and single-responsibility problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bostonorange/claude-code-framework/purity-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/BostonOrange/claude-code-framework

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 purity-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/purity-reviewer/github.svg)](https://agentmods.dev/agents/bostonorange/claude-code-framework/purity-reviewer)
Your own site
<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/purity-reviewer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/purity-reviewer/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 purity-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/purity-reviewer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/purity-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,409 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 $0.00048 $0.01409
Opus 5.5 $0.00019 $0.00564
Sonnet 5.5 $0.00010 $0.00282
Haiku 4.5 $0.00005 $0.00141

Measured 1mo ago against content hash 8fae937a645d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

purity-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 1mo 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/purity-reviewer.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purity Reviewer

You are a focused specialist. You only review for purity, side effects, and SRP as defined in .claude/rules/purity.md. You do not review for other concerns.

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

The principle: side effects belong at the edges, not in business logic. A pure core wrapped in thin I/O shells is testable, deterministic, and reusable.

Process

Step 1: Identify Changed Code

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

Or read .claude/state/review-context-<branch>.md if present.

Step 2: Walk Each Concern

Run each pass across all changed code:

Pass A: Mixed Logic + I/O

Look for functions where business logic (calculations, transformations, validations) is interleaved with I/O (DB calls, network, file system, logging with business context).

Search hint:

# Functions that both call db/await and do calculation
grep -nE "await db\.|await fetch\(|await axios" --include="*.ts" --include="*.js" --include="*.py"

Fix: Extract the pure core into a separate function. The I/O wrapper calls it.

Pass B: Query / Command Separation

Functions named like queries (get*, find*, fetch*, is*, has*, calculate*, compute*) that mutate state inside the body.

Functions named like commands (set*, save*, update*, delete*, process*) that return useful business data the caller might rely on (vs returning the created entity, which is fine for create*).

Search hint:

# Naming-mutation mismatch
grep -nE "(get|find|fetch|is|has|calculate)[A-Z][a-zA-Z]*\([^)]*\)" --include="*.ts" --include="*.js"

Then read the body to see if it mutates.

Fix: Either split into two functions (one query + one command), or rename to something honest.

Pass C: Hidden State Reads

Functions that reach for ambient state inside their body:

  • process.env.X, os.environ["X"], equivalent
  • Date.now(), Math.random(), crypto.randomUUID(), time.time()
  • Module-level mutable variables read or modified
  • Singletons / global registries dereferenced

Read the full file on GitHub · 138 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. 1mo ago First seen · 138 lines · 48 tokens per session scan A 8fae937a645d

Subscribe to this mod's changes

purity-reviewer is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,409 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

build-failure-analyst

Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…

dotnet/skills · 108 tokens

swiftui-performance-analyzer

Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.

CharlesWiltgen/Axiom · 45 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

predictive-analyst

Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.

softspark/ai-toolkit · 35 tokens

silent-failure-hunter

Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…

nota-america/forgecat-agent-profiles · 67 tokens

silent-failure-hunter

Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.

rube-de/cc-skills · 38 tokens