kanso-nuclear

kanso-nuclear is a skill for Claude Code from blakecyze/kanso. It costs 60 tokens per session (2,749 once invoked), scanned A, original, MIT.

A strict code-review checklist focused on the structure of an entire codebase, not only whether the latest change works. It looks for changes that make code harder to understand and maintain over time.

In plain words
What is it for?
Use it for a nuclear review, deep maintainability sweep, whole-codebase structural audit, or harsh review of a branch. It reports findings, guides refactoring, and verifies the result.
Why use it?
It helps expose complexity that ordinary correctness checks can miss, such as moving a problem around without actually simplifying it. This is useful when a branch or refactor needs a particularly demanding review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Part of the kanso plugin — 11 skills, 1 hook shipped together

Good fit Use it for a nuclear review, deep maintainability sweep, whole-codebase structural audit, or harsh review of a branch. It reports findings, guides refactoring, and verifies the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blakecyze/kanso/kanso-nuclear
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.

Any agent
npx skills add blakecyze/kanso --skill kanso-nuclear
Clone the repo
git clone --depth 1 https://github.com/blakecyze/kanso

Made for: Claude Code.

Or install kanso, the plugin that ships this one along with the rest of its 11 skills, 1 hook.

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 kanso-nuclear

README.md
[![agentmods](https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-nuclear/github.svg)](https://agentmods.dev/skills/blakecyze/kanso/kanso-nuclear)
Your own site
<a href="https://agentmods.dev/skills/blakecyze/kanso/kanso-nuclear"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-nuclear/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 kanso-nuclear

Your own site · 80×15
<a href="https://agentmods.dev/skills/blakecyze/kanso/kanso-nuclear"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-nuclear.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,749 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 $0.00060 $0.02749
Opus 5 $0.00030 $0.01375
Sonnet 5 $0.00012 $0.00550
Haiku 4.5 $0.00006 $0.00275

Measured 12d ago against content hash 24e02d98c1e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kanso-nuclear 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 12d 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.

skills/kanso-nuclear/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kanso-nuclear

A structural review that refuses to approve code on the grounds that it works. Where /kanso-audit checks correctness, clarity, consistency, and architecture, this skill is single-minded about structure: whether the change makes the codebase harder to scan a year from now.

The principles from kanso-principles apply, and the standing rule of this skill sharpens them: delete complexity before you move it. A refactor that rearranges the same difficulty is not a refactor — it's relocation.

Always run inline

Findings, the approval gate, refactor handoffs, and the verify result all stay in the calling chat so the user can see them and act on them.

Exception: --fresh for Phase A only

Append --fresh to push the investigation into a read-only subagent (prefer the Explore agent type — read-only by construction). If the harness has no read-only subagent, say so in one line and run Phase A inline; --fresh degrades gracefully. The findings come back as Phase A's output; Phases B (proposal), C (apply), and D (verify) continue inline. Whole-skill context: fork is deliberately not used — only Phase A benefits from fresh context. Use this when the current session has already touched the code — fresh context cuts the anchoring on prior decisions in the transcript. On all-mode runs over large repos, --fresh is usually the right default to keep the main chat readable.

Resolve the scope

$ARGUMENTS selects:

  • (empty) or all → the whole codebase. The marquee invocation.
  • diff or branch → commits on the current branch vs upstream or main.
  • a path like src/billing/ → everything under that path.

If diff mode finds nothing staged or committed, fall back to the last commit and tell the user.

Before any review:

  • Shape of the repo: !git ls-files | wc -l
  • Largest files first (they are the most likely Phase B targets): !git ls-files | xargs wc -l 2>/dev/null | sort -rn | head -20
  • Voice calibration: !git log -n 20 --oneline
  • Existing conventions: read AGENTS.md, CLAUDE.md, CONTRIBUTING.md, linter configs

Read the full file on GitHub · 199 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. 12d ago First seen · 199 lines · 60 tokens per session scan A 24e02d98c1e6

Subscribe to this mod's changes

kanso-nuclear is a skill published in the GitHub repository blakecyze/kanso (3 stars, last pushed 8d ago), licensed MIT. It adds 60 tokens to every session and 2,749 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

code-reviewer

Code review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.

claude-world/director-mode-lite · 59 tokens

mutation-test

Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…

greglas75/zuvo · 190 tokens

review

Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.

greglas75/zuvo · 70 tokens

db-audit

Database performance and safety audit. 70+ checks across 13 dimensions (DB1-DB13): query patterns, indexes, schema design, connections, transactions, migrations, caching, query optimization, ORM anti-patterns, observability, data lifecycle, DB security, and migration deployment safety. Code-level checks for all ORMs.…

greglas75/zuvo · 115 tokens

write-tests

Write tests for existing production code. Processes ONE file at a time through a full pipeline: analyze, inventory (frozen BEFORE writing), write, executable coverage gate, verify, blind coverage audit, adversarial review, log. Uses CodeSift for discovery and analysis when available. Modes: [path] (specific target)…

greglas75/zuvo · 87 tokens

brainstorm

Explores a codebase, researches the problem space, and produces an approved design specification before any code is written. Use when the user wants to create a new feature, add significant functionality, redesign a subsystem, or build something that touches multiple parts of the project.

greglas75/zuvo · 56 tokens