debug

A command that investigates a failing test or software bug by tracing it to its underlying cause. It records the symptom, evidence, proposed fix, and verification result.

In plain words
What is it for?
Use it to reproduce failures, examine relevant files, identify the root cause, apply a justified fix, and run tests to check the result.
Why use it?
It prevents fixes that only hide the visible error, such as skipping a test or catching an exception without understanding the problem. It also stops and reports when the cause cannot be found.

Command for Claude Code

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 commands/rex/mcp-rancher/debug
Clone the repo
git clone --depth 1 https://github.com/rex/mcp-rancher

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 204 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 $0.00013 $0.00204
Opus 5 $0.00006 $0.00102
Sonnet 5 $0.00003 $0.00041
Haiku 4.5 $0.00001 $0.00020

Measured yesterday against content hash 3dac4f3acf0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • debug — 100% identical, 0 lines differ
.claude/commands/debug.md · 20 lines

What it actually says

Debug: $ARGUMENTS

  1. If a failing test was given, run it and capture the exact output first.
  2. Spawn debugger subagent with the error, repro steps, and relevant file paths.
  3. debugger returns: symptom / root cause / evidence / fix / verification.
  4. If debugger can't find root cause in 5 hypotheses, STOP and report.
  5. If the fix is applied, spawn test-runner to verify.

Escalate to Opus (debugger with model: opus) if the repro fails twice.

Never fix symptoms. If the fix is "catch the exception" or "skip the test," stop and ask the human.

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 · 20 lines · 13 tokens per session scan A 3dac4f3acf0c

Subscribe to this mod's changes

debug is a command published in the GitHub repository rex/mcp-rancher (1 stars, last pushed 6d ago), licensed MIT. It adds 13 tokens to every session and 204 once invoked, about $0.0001 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.