debug

A debugging command that follows a checklist: reproduce the problem, read the full error, locate its source, make a focused fix, and verify the result.

In plain words
What is it for?
Use it to investigate errors involving inputs, null values, types, asynchronous code, environment settings, or recent changes, while adding a test that reproduces the bug.
Why use it?
It guides investigation toward the underlying cause instead of hiding symptoms with unrelated changes or broad error handling.

Command

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/jsk9999/ai-nexus/debug
Clone the repo
git clone --depth 1 https://github.com/JSK9999/ai-nexus
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 245 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 $0.00004 $0.00245
Opus 5 $0.00002 $0.00122
Sonnet 5 $0.00001 $0.00049
Haiku 4.5 $0.00000 $0.00024

Measured 2d ago against content hash 38286170c3d4, 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 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.

config/commands/debug.md · 32 lines

What it actually says

/debug

When asked to debug an issue:

  1. Reproduce — Understand the exact steps to trigger the bug
  2. Read error — Analyze the full error message and stack trace
  3. Locate — Find the exact line/function where the error originates
  4. Understand — Read surrounding code to understand intended behavior
  5. Fix — Make the minimal change to fix the root cause
  6. Verify — Run tests or demonstrate the fix works

Debugging Checklist

  • Read the full error message and stack trace
  • Check recent changes (git diff, git log)
  • Verify inputs at the failure point
  • Check for null/undefined values
  • Check for type mismatches
  • Check async/await and promise handling
  • Check environment variables and config

Rules

  • Fix the root cause, not the symptom
  • Don't add try/catch to hide errors
  • Don't change unrelated code while debugging
  • Write a test that reproduces the bug before fixing
  • Explain what caused the bug and why the fix works
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 · 32 lines · 4 tokens per session scan A 38286170c3d4

Subscribe to this mod's changes

debug is a command published in the GitHub repository JSK9999/ai-nexus (18 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 4 tokens to every session and 245 once invoked, about $0.0000 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.