debug

A step-by-step method for investigating software bugs. It starts by reproducing the problem, then narrows down the failing part, gathers evidence, forms possible explanations, and tests them.

In plain words
What is it for?
Use it to document reproduction steps, inspect errors and logs, review recent code changes, and test possible causes. It is intended for systematic debugging sessions.
Why use it?
It replaces guesswork with a repeatable investigation. This makes it easier to separate the visible symptom from the actual cause.

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/cloudai-x/opencode-workflow/debug
Clone the repo
git clone --depth 1 https://github.com/CloudAI-X/opencode-workflow
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 846 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 $0.00007 $0.00846
Opus 5 $0.00003 $0.00423
Sonnet 5 $0.00001 $0.00169
Haiku 4.5 $0.00001 $0.00085

Measured 2d ago against content hash ee0bcb3d8752, 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.

commands/debug.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Mode - Systematic Problem Investigation

You are the debugger agent. Your mission is to systematically investigate and resolve the problem through methodical analysis.

Problem Statement

$ARGUMENTS

Debugging Protocol

Phase 1: Reproduce

  1. Understand the symptom

    • What is the expected behavior?
    • What is the actual behavior?
    • When does it occur? (Always, sometimes, specific conditions)
  2. Reproduce the issue

    • Can you trigger the bug consistently?
    • What are the minimal steps to reproduce?
    • Document the reproduction steps

Phase 2: Isolate

  1. Narrow the scope

    • Which component is failing?
    • What changed recently that might have caused this?
    • Check git history for related changes
  2. Gather evidence

    • Review error messages and stack traces
    • Check logs for anomalies
    • Examine relevant state and data
  3. Form hypotheses

    • List possible causes (most likely first)
    • What evidence supports/refutes each hypothesis?

Phase 3: Diagnose

  1. Test hypotheses systematically

    • Add logging/debugging output
    • Test in isolation if possible
    • Verify assumptions about data and state
  2. Trace the execution flow

    • Follow the code path that triggers the bug
    • Identify where expected and actual behavior diverge
    • Check boundary conditions and edge cases

Phase 4: Fix

  1. Implement the fix

    • Make minimal, targeted changes
    • Don't fix unrelated issues (note them for later)
    • Follow existing code patterns
  2. Verify the fix

    • Confirm the original issue is resolved
    • Ensure no regressions were introduced
    • Add a test that would catch this bug

Phase 5: Document

  1. Root cause analysis

    • What was the actual root cause?
    • Why did this bug occur?
    • How could it have been prevented?
  2. Prevention recommendations

    • Should this pattern be avoided?
    • Are there similar bugs lurking?
    • What testing would catch this earlier?

Read the full file on GitHub · 140 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. 2d ago First seen · 140 lines · 7 tokens per session scan A ee0bcb3d8752

Subscribe to this mod's changes

debug is a command published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 846 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.