debug

debug is a command for coding agents from KaimingWan/oh-my-kiro. It costs 0 tokens per session (1,284 once invoked), scanned A, original, MIT.

A structured debugging command that investigates the cause of a software problem before any fix is made. It keeps an investigation document with the problem, ruled-out causes, evidence, and decisions.

In plain words
What is it for?
Use it to resume or start a bug investigation, inspect prior evidence, perform systematic triage, and document the root-cause analysis.
Why use it?
It prevents guesswork and repeated investigation across sessions by preserving the current findings.

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/kaimingwan/oh-my-kiro/debug
Clone the repo
git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro

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 debug

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/debug.svg)](https://agentmods.dev/commands/kaimingwan/oh-my-kiro/debug)
Your own site
<a href="https://agentmods.dev/commands/kaimingwan/oh-my-kiro/debug"><img src="https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/debug.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 1,284 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 $0.00000 $0.01284
Opus 5 $0.00000 $0.00642
Sonnet 5 $0.00000 $0.00257
Haiku 4.5 $0.00000 $0.00128

Measured 5d ago against content hash 81f78b8773a2, 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 5d 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.

commands/debug.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You MUST follow this exact sequence. @debug is a fully automated debugging pipeline — no user confirmation between stages. The goal is systematic root cause analysis, not guess-and-check.

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST

Stage 0: Session Resume Check

Before starting any investigation, check for existing investigation documents:

  1. List docs/investigations/ — look for files matching the current bug topic
  2. If a matching document exists:
    • Read its Status Overview section to understand current state
    • Read its Ruled Out section to avoid re-investigating dead ends
    • Read its Decision Log to understand prior decisions
    • Resume from the last recorded state — do NOT restart from scratch
  3. If no matching document exists:
    • Create docs/investigations/{date}-{topic}.md using skills/omk-debugging/investigation-template.md as template
    • Fill in the Problem Statement with the user's bug report

Session Resume Protocol: Every new session MUST check docs/investigations/ first. The investigation document is the single source of truth for cross-session continuity.

Stage 1: Triage & Context

  1. Read knowledge/episodes.md — check if this bug pattern has occurred before
  2. Build Architectural Context around the bug:
    • generate_codebase_overview → module structure
    • find_references on bug's core symbol(s) → all callers
    • get_document_symbols on bug's file(s) → internal structure
  3. Classify failure type:
Category Signal
Logic/Semantic Test fails, wrong output
Environment/Config Works locally, fails elsewhere
Concurrency/Timing Intermittent
Invalid Invocation Schema error, 400 response
Under-specified Intent Need more context
  1. Write triage summary to the investigation document (docs/investigations/{date}-{topic}.md):
    • Fill in Problem Statement
    • Add initial entries to Evidence Table (L0 facts from diagnostics)
    • Build initial Investigation Tree with top-level branches
    • Update Status Overview with triage results and next steps

Read the full file on GitHub · 141 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. 5d ago First seen · 141 lines · 0 tokens per session scan A 81f78b8773a2

Subscribe to this mod's changes

debug is a command published in the GitHub repository KaimingWan/oh-my-kiro (103 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,284 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 2026-08-30.