ai-engineering-fluency: Agent for Claude Code

.claude/agents/refactor-large-function.md

refactor-large-function is an agent for Claude Code from rajbos/ai-engineering-fluency. It costs 30 tokens per session (1,142 once invoked), scanned A, original, MIT.

A refactoring helper for functions flagged as too long or complex by ESLint, a tool that checks code rules. It splits one selected function into smaller helpers and checks that tests continue to pass.

In plain words
What is it for?
Use it to select one long function, extract focused private helpers, and verify the result with the existing tests.
Why use it?
Very large functions are harder to read, test, and change safely. Breaking one into focused parts can make its logic easier to understand without changing its behaviour.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is rajbos/ai-engineering-fluency's own configuration. It tells Claude Code how to work on ai-engineering-fluency itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-engineering-fluency configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rajbos/ai-engineering-fluency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rajbos/ai-engineering-fluency/main/.claude/agents/refactor-large-function.md
Clone the repo
git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency

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-large-function

README.md
[![agentmods](https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/refactor-large-function/github.svg)](https://agentmods.dev/agents/rajbos/ai-engineering-fluency/refactor-large-function)
Your own site
<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/refactor-large-function"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/refactor-large-function/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-large-function

Your own site · 80×15
<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/refactor-large-function"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/refactor-large-function.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,142 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 $0.00030 $0.01142
Opus 5.5 $0.00012 $0.00457
Sonnet 5.5 $0.00006 $0.00228
Haiku 4.5 $0.00003 $0.00114

Measured yesterday against content hash 0347f3bf9659, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refactor-large-function 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 yesterday.

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.

.claude/agents/refactor-large-function.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor Large Function

An ESLint complexity or max-lines-per-function rule is producing warnings for functions that are too long. Pick one of those functions (not from extension.ts, which is intentionally monolithic) and refactor it into smaller, focused private helpers.

Step 1 - Identify the target

Run ESLint with the complexity rules to get the current list of violations:

cd vscode-extension && node_modules/.bin/eslint src --rule '{"max-lines-per-function": ["warn", 80]}' --format stylish 2>&1 | grep "Lines/Fn\|max-lines-per-function" | head -20

Or, if the project already has the rule configured, just run:

cd vscode-extension && node_modules/.bin/eslint src 2>&1 | grep "max-lines-per-function\|Lines/Fn" | head -20

Choose one function to refactor, following these priorities:

  1. Skip src/extension.ts - it is intentionally large and hard to test in isolation.
  2. Prefer files that already have unit tests (check test/unit/ for a matching test file).
  3. Among the remaining candidates, pick the one with the clearest logical sections (wizard steps, processing phases, format branches, etc.) - those decompose most cleanly.

Step 2 - Read the instructions file

Before touching any code, read the relevant sub-project instructions file. For vscode-extension/ work, read .github/instructions/vscode-extension.instructions.md.

Step 3 - Understand the function

Read the full function body and identify natural decomposition boundaries:

  • Wizard / multi-step UI flows: each step becomes a private method returning null on cancellation.
  • Format dispatch (e.g. JSONL vs JSON vs delta): each format branch becomes its own function.
  • Multi-phase processing: setup / main loop / finalization each become their own function.
  • Complex sub-operations inside a branch that push complexity above the threshold: extract them too.

Introduce small result interfaces or types at the top of the file (not exported) to carry data between steps cleanly, rather than long parameter lists.

Read the full file on GitHub · 115 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. yesterday First seen · 115 lines · 30 tokens per session scan A 0347f3bf9659

Subscribe to this mod's changes

refactor-large-function is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,142 once invoked, about $0.0001 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 2026-10-26.

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

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

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