debug

A command for investigating errors or unexpected behaviour in a systematic way.

In plain words
What is it for?
Use it to debug a failing feature, trace an error through the application, identify the root cause, and document how to avoid it later.
Why use it?
It organizes the symptoms, possible causes, evidence, fix, and prevention steps instead of guessing at the problem.

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/felipeslo/opencode-kit/debug
Clone the repo
git clone --depth 1 https://github.com/felipeslo/opencode-kit
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 433 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 $0.00433
Opus 5 $0.00006 $0.00217
Sonnet 5 $0.00003 $0.00087
Haiku 4.5 $0.00001 $0.00043

Measured yesterday against content hash 96af93058370, 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.

.opencode/commands/debug.md · 104 lines

What it actually says

/debug - Systematic Problem Investigation

$ARGUMENTS


Purpose

This command activates DEBUG mode for systematic investigation of issues, errors, or unexpected behavior.


Behavior

When /debug is triggered:

  1. Gather information

    • Error message
    • Reproduction steps
    • Expected vs actual behavior
    • Recent changes
  2. Form hypotheses

    • List possible causes
    • Order by likelihood
  3. Investigate systematically

    • Test each hypothesis
    • Check logs, data flow
    • Use elimination method
  4. Fix and prevent

    • Apply fix
    • Explain root cause
    • Add prevention measures

Output Format

## 🔍 Debug: [Issue]

### 1. Symptom
[What's happening]

### 2. Information Gathered
- Error: `[error message]`
- File: `[filepath]`
- Line: [line number]

### 3. Hypotheses
1. ❓ [Most likely cause]
2. ❓ [Second possibility]
3. ❓ [Less likely cause]

### 4. Investigation

**Testing hypothesis 1:**
[What I checked] → [Result]

**Testing hypothesis 2:**
[What I checked] → [Result]

### 5. Root Cause
🎯 **[Explanation of why this happened]**

### 6. Fix
```[language]
// Before
[broken code]

// After
[fixed code]

7. Prevention

🛡️ [How to prevent this in the future]


---

## Examples

/debug login not working /debug API returns 500 /debug form doesn't submit /debug data not saving


---

## Key Principles

- **Ask before assuming** - get full error context
- **Test hypotheses** - don't guess randomly
- **Explain why** - not just what to fix
- **Prevent recurrence** - add tests, validation
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 · 104 lines · 13 tokens per session scan A 96af93058370

Subscribe to this mod's changes

debug is a command published in the GitHub repository felipeslo/opencode-kit (2 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 433 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.