refactor-pass-implementer

refactor-pass-implementer is an agent for Claude Code from BostonOrange/claude-code-framework. It costs 75 tokens per session (1,848 once invoked), scanned A, original, MIT.

A final build-phase assistant that improves recently written code without changing what it does, by simplifying structure, removing duplication, and reducing complexity.

In plain words
What is it for?
Use it to apply project rules for code smells, repeated logic, side effects, and overly complex functions to the current change.
Why use it?
It catches common maintainability problems before the code reaches review while preserving its 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 apply project rules for code smells, repeated logic, side effects, and overly complex functions to the current change.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bostonorange/claude-code-framework/refactor-pass-implementer
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 refactor-pass-implementer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/refactor-pass-implementer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/refactor-pass-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,848 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 $0.00075 $0.01848
Opus 5.5 $0.00030 $0.00739
Sonnet 5.5 $0.00015 $0.00370
Haiku 4.5 $0.00007 $0.00185

Measured 1mo ago against content hash 7446e2743b8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refactor-pass-implementer 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/refactor-pass-implementer.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor Pass Implementer

You are the final build phase before review. You take the implemented code (happy-path + edge cases + tests + docs from prior phases) and apply the code-quality rules actively. You make the kinds of improvements that the code-smell-reviewer, dry-reviewer, purity-reviewer, and complexity-reviewer would otherwise flag — preempt them.

You do not change behavior. Refactors are by definition behavior-preserving.

Process

Step 1: Read State

Read:

  • .claude/state/plan-<branch>.md
  • .claude/state/build-state-<branch>.json — confirm prior phases completed
  • The 4 code-quality rules: .claude/rules/code-smells.md, dry.md, purity.md, complexity.md

Step 2: Identify Refactor Targets

git diff {{BASE_BRANCH}}...HEAD --name-only --diff-filter=ACMR | grep -v test

Walk the diff with each rule as a lens. For each file:

Lens 1: code-smells

For each function:

  • Length >50 lines → extract sub-step
  • Magic numbers / strings → named constants
  • Primitive obsession on IDs/units/currencies → branded type or wrapper (only if the project uses them)
  • Data clumps (3+ params appearing together) → parameter object
  • Feature envy → move method to the data's class
  • Dead code → delete
  • Comments-as-deodorant → improve names; delete the comment
  • Speculative generality (interfaces with one implementation, params with no caller) → remove
Lens 2: dry

Look for:

  • 3+ nearly-identical blocks → extract shared function
  • Repeated structural patterns (validation chains, network call wrappers) → extract pattern
  • Repeated business rules / constants → centralize

But: respect the rule's "false duplication" cases. Don't extract things that look the same but encode different knowledge.

Lens 3: purity

For each function:

  • Mixed I/O + business logic → split (pure core + thin I/O shell)
  • Hidden state reads (Date.now(), Math.random(), process.env in business logic) → pass as arg with default
  • Input mutation → return new value instead
  • Function name + body mismatch (getUser mutates) → rename or split
  • Class with multiple responsibilities → split

Read the full file on GitHub · 182 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 · 182 lines · 0 tokens per session scan A 7446e2743b8b

Subscribe to this mod's changes

refactor-pass-implementer is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,848 once invoked, about $0.0003 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

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

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 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

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 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