code-generation

A guide for Java code generators that assemble source code from strings. It keeps each generated output line aligned with one Java source line by using formatter-off markers.

In plain words
What is it for?
Use it when writing, reviewing, or fixing Java generators that build source code with string concatenation, especially when template strings contain newline characters.
Why use it?
Automatic formatting can split string-concatenation code across lines and make the generated source harder to follow or incorrect. This guide helps prevent that layout from being changed.

Skill for Claude CodeCodex

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 skills/motlin/claude-code-plugins/code-generation
Any agent
npx skills add motlin/claude-code-plugins --skill code-generation
Clone the repo
git clone --depth 1 https://github.com/motlin/claude-code-plugins

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 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.

ModelPer sessionOnce invoked
Fable 5 $0.00089 $0.00805
Opus 5 $0.00044 $0.00402
Sonnet 5 $0.00018 $0.00161
Haiku 4.5 $0.00009 $0.00081

Measured 2d ago against content hash 52426224aeac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-generation 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.

plugins/code/skills/code-generation/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Generation Formatting

Purpose

Java code generators that build source code via string concatenation must use // @formatter:off / // @formatter:on guards. Without these, IntelliJ's auto-formatter breaks concatenation chains across multiple lines, destroying the correspondence between Java source lines and generated output lines.

The Rule

Each line of generated output (terminated by \n) must occupy a single Java source line. A new line in the Java source should only occur where there is a \n in the template string.

Bad (auto-formatted)

setterBody = ""
    + "            domainObject.get"
    + propNameUpper
    + "().clear();\n"
    + "            return;\n";

Good (one output line per Java line)

// @formatter:off
setterBody = ""
        + "            domainObject.get" + propNameUpper + "().clear();\n"
        + "            return;\n";
// @formatter:on

How to Identify Violations

Search for string concatenation blocks that contain \n literals but are NOT wrapped in // @formatter:off. Common patterns:

  1. Multi-line + chains where each + is on its own line and template variables are separated from their surrounding string literals
  2. .collect() lambdas producing single-line templates that got broken across multiple lines
  3. Return statements wrapped in parentheses return ( "" + ... ) instead of direct return "" + ...

Fix Procedure

  1. Search generator files for string concatenation containing \n that lacks @formatter:off guards
  2. For each violation:
    • Add // @formatter:off before the block
    • Collapse string concatenation so each \n-terminated segment is on one Java source line
    • Add // @formatter:on after the block
  3. For .collect() lambdas that produce single-line templates (one \n), collapse the entire template string onto one line
  4. For multi-line templates, each \n-terminated segment gets its own line with + continuation
  5. Use the same indentation style as existing @formatter:off blocks in the file

Read the full file on GitHub · 84 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. 2d ago First seen · 84 lines · 89 tokens per session scan A 52426224aeac

Subscribe to this mod's changes

code-generation is a skill published in the GitHub repository motlin/claude-code-plugins (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 89 tokens to every session and 805 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens