automagik-cli: Command for Claude Code

.claude/commands/nuke.md

nuke is a command for Claude Code from namastexlabs/automagik-cli. It costs 0 tokens per session (4,398 once invoked), scanned A, original, MIT.

A debugging command for difficult bugs that investigates a problem across multiple components and uses parallel checks with recovery points.

In plain words
What is it for?
Use it to investigate complex or mysterious failures, including bugs spanning several services or components.
Why use it?
It is intended for problems that remain unresolved after ordinary debugging, such as race conditions, memory leaks, integration failures, or production incidents.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is namastexlabs/automagik-cli's own configuration. It tells Claude Code how to work on automagik-cli 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 automagik-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to namastexlabs/automagik-cli. 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/namastexlabs/automagik-cli/main/.claude/commands/nuke.md
Clone the repo
git clone --depth 1 https://github.com/namastexlabs/automagik-cli

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 nuke

README.md
[![agentmods](https://agentmods.dev/badge/commands/namastexlabs/automagik-cli/nuke.svg)](https://agentmods.dev/commands/namastexlabs/automagik-cli/nuke)
Your own site
<a href="https://agentmods.dev/commands/namastexlabs/automagik-cli/nuke"><img src="https://agentmods.dev/badge/commands/namastexlabs/automagik-cli/nuke.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,398 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 $0.00000 $0.04398
Opus 5 $0.00000 $0.02199
Sonnet 5 $0.00000 $0.00880
Haiku 4.5 $0.00000 $0.00440

Measured 3d ago against content hash 82c06266bd4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nuke 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 3d 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.

.claude/commands/nuke.md · 527 lines

How it starts

The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/nuke


allowed-tools: Task(), Read(), Write(), Edit(), MultiEdit(), Glob(), Grep(), Bash(), LS(), mcp__zen__, mcp__genie-memory__, mcp__send_whatsapp_message__ description: Enhanced 3-Layer Parallel Nuclear Debugging with Checkpoint Recovery

🚨 NUCLEAR DEBUGGING 🚨

When traditional debugging fails, /nuke systematically tests ALL zen combinations to find the solution.

When to Use /nuke

  • After standard debugging fails: Tried /debug, manual investigation
  • Complex/mysterious bugs: Race conditions, memory leaks, integration issues
  • Critical production issues: Need solution ASAP, willing to use all resources
  • Multi-system problems: Bug spans multiple components/services
  • Simple issues: Use regular /debug first
  • Known patterns: Search memory first

Usage

# Basic nuclear debugging
/nuke "Ana team routes to wrong agent on Portuguese queries about cartão"

# With specific focus
/nuke "Memory leak in agent sessions after 1000+ requests" focus="performance,memory"

# With time limit (default: 30 minutes)
/nuke "Race condition in payment processing" time_limit="45m"

Enhanced 3-Layer Parallel Nuclear Architecture

🔍 Layer 1: Parallel Investigation

Smart model selection for optimal analysis

Model Selection Strategy:

investigation_models:
  complex_systems: "gemini-2.5-pro"     # 1M context, thinking mode
  logical_debugging: "o3"               # Strong reasoning chains  
  performance_analysis: "grok"          # Large context analysis
  quick_patterns: "o4-mini"             # Fast pattern recognition
  architectural_review: "gemini-2.5-pro" # Deep architectural insight

Parallel Investigation Execution:

  • Task 1: mcp__zen__debug - Traditional debugging workflow
  • Task 2: mcp__zen__analyze - Architectural analysis
  • Task 3: mcp__zen__thinkdeep - Deep investigation
  • Task 4: mcp__zen__tracer - Code flow tracing (if code-related)

Read the full file on GitHub · 527 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. 3d ago First seen · 527 lines · 0 tokens per session scan A 82c06266bd4e

Subscribe to this mod's changes

nuke is a command published in the GitHub repository namastexlabs/automagik-cli (6 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,398 tokens. 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 2026-09-04.