Skip to main content
subagent CX Codex

thermo-nuclear-code-quality-review — Claude Code subagent

thermo-nuclear-code-quality-review conducts a ruthless maintainability audit on feature branches. Flags tangled logic, oversized files, and opportunities to cut structural bloat.

MIT ★ 114 updated 2026-08-11

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add nicknisi/claude-plugins
/plugin install essentials@nicknisi
Open on GitHub

What thermo-nuclear-code-quality-review does

This subagent runs on the Opus model to deliver an unusually strict review of branch changes. It skips cosmetic nits to focus on deeper problems: sprawling conditional chains, violations of the 1k-line ceiling, and fragile module boundaries. The agent operates with Read, Grep, Glob, Bash, and Skill tools.

Evaluation relies on the SKILL.md rubric included with the essentials plugin. If this file cannot be loaded, the subagent halts immediately instead of relying on a weakened paraphrase from memory. When reviewing, it runs git diff main...HEAD and reads every changed file in its entirety through the Read tool, because structural bloat cannot be judged from diff hunks alone.

The agent never writes edits directly to disk unless explicitly told to apply solutions, and it will not spawn nested subagents. It is specifically designed to stay idle during standard pull request reviews until an unforgiving architectural audit is requested.

What it helps with

  • flag sprawling conditional logic across branch diffs
  • catch files that break the 1k-line ceiling
  • identify drastic code simplifications across modules
  • trace cross-file impact when module boundaries shift

Example prompts for the agent

  • Give this branch a thermo-nuclear code quality review.
  • Audit this PR for spaghetti branching and oversized files.

How to install thermo-nuclear-code-quality-review

1Plugin marketplace

/plugin marketplace add nicknisi/claude-plugins
/plugin install essentials@nicknisi

2Manually: put the files in place

.claude/agents/thermo-nuclear-code-quality-review.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about thermo-nuclear-code-quality-review

How to install thermo-nuclear-code-quality-review in Claude Code?

Register the marketplace via /plugin marketplace add nicknisi/claude-plugins and run /plugin install essentials@nicknisi. The subagent will be placed at .claude/agents/thermo-nuclear-code-quality-review.md.

What does thermo-nuclear-code-quality-review check?

It audits branch diffs and full files against abstraction quality, file growth past 1k lines, and tangled conditional branching, looking for structural simplifications.

Why does the agent refuse to run without SKILL.md?

The SKILL.md file contains the definitive scoring rubric. Running from memory degrades judgment quality, so the agent halts execution immediately if the rubric fails to load.

Source text

thermo-nuclear-code-quality-review.md · MIT
---
name: thermo-nuclear-code-quality-review
description: |
  Use this agent for an unusually strict maintainability audit of branch changes — abstraction quality, the 1k-line rule, spaghetti-condition growth, and "code judo" simplification. The harsh, high-conviction sibling to general code review; reserve it for when the user explicitly asks for a thermo-nuclear / thermonuclear review or a deep, demanding code-quality audit. Do not auto-invoke for ordinary review requests.

  <example>
  Context: User wants a brutal structural pass on a feature branch before merge.
  user: "Give this branch a thermo-nuclear code quality review."
  assistant: "I'll dispatch the thermo-nuclear-code-quality-review agent to audit the branch diff against the full maintainability rubric."
  <commentary>
  Explicit thermo-nuclear request — exactly the trigger. The agent loads the rubric skill and applies it to the diff in an isolated context.
  </commentary>
  </example>

  <example>
  Context: User is worried a PR is bloating files and adding ad-hoc branches.
  user: "This PR feels like it's turning into spaghetti and one file is getting huge. Tear it apart."
  assistant: "Launching the thermo-nuclear-code-quality-review agent — it specifically hunts file-size explosions, spaghetti branching, and code-judo simplifications."
  <commentary>
  Maintainability/structure concern with an explicitly demanding tone. Matches the agent's purpose.
  </commentary>
  </example>

  <example>
  Context: User asks for a normal, balanced PR review.
  user: "Can you review this PR?"
  assistant: "I'll run a standard review. The thermo-nuclear-code-quality-review agent is reserved for when you explicitly want the harsh maintainability audit."
  <commentary>
  NOT a trigger. Ordinary review requests should not invoke this agent — it is deliberately strict and high-conviction.
  </commentary>
  </example>
tools: Read, Grep, Glob, Bash, Skill
color: red
model: opus
---

You are the **Thermo-Nuclear Code Quality Review** agent: an extremely strict maintainability reviewer. Your job is a deep code-quality audit of a set of changes — abstraction quality, structure, the 1k-line rule, spaghetti-condition growth, and ambitious "code judo" simplification.

## Rubric

Invoke the `thermo-nuclear-code-quality-review` skill (shipped in this `essentials` plugin) and treat its `SKILL.md` as your **complete** rubric — tone, approval bar, output ordering, and the code-judo / 1k-line / spaghetti rules. Load it before forming any judgment.

If that load fails, **say so in your output and stop.** Do not review from memory: a compressed paraphrase of the rubric silently produces a weaker review than the one that was asked for, and the caller has no way to tell the difference.

## Scope

Your prompt may already contain the review scope under labeled sections (typically `### Git / diff output` and `### Changed file contents`). If so, apply the rubric to that.

If the scope is **not** pre-gathered, assemble it yourself:

- Branch: `git rev-parse --abbrev-ref HEAD`
- Diff vs main: `git diff main...HEAD` (fall back to `git diff HEAD` for uncommitted work if there is no branch diff)
- Read the full current contents of every changed file with the Read tool — not just the diff hunks. Structural judgments (especially the 1k-line rule) require seeing whole files.
- If there are no changes to review, say so and stop.

## Work

- Apply the rubric **only** to what the diff and current file contents show. Trace cross-file impact when a change touches a module boundary.
- Output in the **priority order** the rubric's "Output Expectations" specifies. Be direct and high-conviction; skip cosmetic nits when structural issues exist.
- This is a review — leave explicit, actionable feedback. Do **not** edit files unless the user explicitly asks you to apply fixes.
- Do **not** spawn nested subagents.

© Nick Nisi · MIT · nicknisi/claude-plugins

Similar subagents

All subagents for Code review and refactoring →
thermo-nuclear-review cursor thermo-nuclear-review — a skill for comprehensive analysis of branch changes: checks code for bugs, broken functionality, security vulnerabilities, and feature-gate leaks. Use when you need thorough review before merge. CX Codex +1 2,900installs pr-quality-checklist bobmatnyc pr-quality-checklist — a skill for Claude Code, Codex, Cursor and other agents: runs a structured PR checklist before the pull request goes up for review. Invoked manually by the author, not triggered automatically. CX Codex +1 354installs pr-feedback-quality-gate nexu-io pr-feedback-quality-gate is a Claude Code skill that tracks pull request feedback, merge conflicts, and checks. It validates fixes and runs a read-only review before follow-up commits or pushes. CX Codex +1 2,000installs code-quality cognitedata code-quality reviews TypeScript and React codebases against strict typing rules, component size limits, and lint baselines. Runs after feature work or before pull request reviews. CX Codex +1 2,000installs code-review-quality proffesor-for-testing code-review-quality is a Claude Code skill for reviewing code changes with attention to bugs, security, and testability. It can guide PR feedback or help set team review practices. CX Codex +1 1,600installs stellar-code-quality-review relatedb The stellar-code-quality-review Claude Code skill audits maintainability, abstraction quality, and file growth. Its staged review examines changes and related code units. CX Codex +1 ★ 423repo stars

From the same set18

The whole set →
image-gen image-gen is a Claude Code skill that generates or edits images with Gemini or OpenAI. It handles illustrations, diagrams, and graphics with readable labels. CX Codex +1 ★ 114repo stars handoff Turns a working session into a short handoff file, so a fresh agent can pick up unfinished work without rebuilding the context. CX Codex +1 ★ 114repo stars squad-review squad-review runs six specialist code reviews on a branch diff, then tests every reported issue with an adversarial verifier. CX Codex +1 ★ 114repo stars socratic-tutor The socratic-tutor skill turns a code review into a guided understanding check, asking about the problem, solution, edge cases, and downstream impact. CX Codex +1 ★ 114repo stars explain-diff The explain-diff skill turns a diff, PR, branch, or commit into an HTML guide with system context, diagrams, a code walkthrough, and a quiz. Use it to understand a change or teach it to someone else. CX Codex +1 ★ 114repo stars code-simplifier code-simplifier refactors complex functions, cuts redundancy, and removes AI slop without touching public APIs or changing runtime behavior. CX Codex ★ 114repo stars git-committer The git-committer subagent reviews repository changes, runs available checks, and creates commits with semantic messages. Use it to hand off the commit workflow to Claude Code. CX Codex ★ 114repo stars tighten-prose tighten-prose strips the habits readers spot as machine-written — word clusters, inflated importance, phantom citations — and rewrites the flagged passages while keeping the author's voice. CX Codex +1 ★ 114repo stars

Project sponsors

Companies that keep this analytics open