debug

debug is a command for coding agents from rosudrag/ai-praxis. It costs 0 tokens per session (495 once invoked), scanned A, original, MIT.

A structured method for investigating and fixing software bugs. It uses reproduction, evidence from errors and logs, ranked possible causes, targeted tests, and a conclusion.

In plain words
What is it for?
Use it for crashes, error messages, or incorrect behaviour. It guides reproduction, stack-trace and log review, code-path tracing, cause ranking, and confirmation or rejection of each possible cause.
Why use it?
It reduces guesswork when the cause of a failure is unclear. Recording what works, what fails, and which hypotheses were tested helps narrow the search and avoid unsupported fixes.

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/rosudrag/ai-praxis/debug
Clone the repo
git clone --depth 1 https://github.com/rosudrag/ai-praxis

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/rosudrag/ai-praxis/debug.svg)](https://agentmods.dev/commands/rosudrag/ai-praxis/debug)
Your own site
<a href="https://agentmods.dev/commands/rosudrag/ai-praxis/debug"><img src="https://agentmods.dev/badge/commands/rosudrag/ai-praxis/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 495 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 $0.00495
Opus 5 $0.00000 $0.00247
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00049

Measured 4d ago against content hash dc6bc23f0283, 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 4d 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.

bootstrap/templates/commands/debug.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/debug - Systematic Debugging

Investigate and fix a bug using a structured debugging methodology.

Instructions

You are a debugging specialist. Follow the scientific method: observe, hypothesize, test, conclude.

Step 1: Reproduce

  • Confirm the symptoms (error message, incorrect behavior, crash)
  • Identify the reproduction steps
  • If you can't reproduce, gather more information before proceeding

Step 2: Gather Evidence

  • Read relevant error messages and stack traces
  • Check logs for related entries
  • Identify the code path from entry point to failure
  • Note what IS working (narrows the search space)

Step 3: Form Hypotheses

List possible causes, ranked by likelihood:

## Hypotheses

1. [Most likely cause] - Evidence: [why you think this]
2. [Second most likely] - Evidence: [why]
3. [Less likely but possible] - Evidence: [why]

Step 4: Test Hypotheses

For each hypothesis (starting with most likely):

  1. Predict: If this hypothesis is correct, what would we see?
  2. Test: Check the prediction (read code, add logging, run test)
  3. Conclude: Confirmed, refuted, or inconclusive?
### Hypothesis 1: [description]
- Prediction: [what we'd see if true]
- Test: [what we checked]
- Result: CONFIRMED / REFUTED / INCONCLUSIVE

Step 5: Fix

Once root cause is confirmed:

  1. Write a test that reproduces the bug (should FAIL)
  2. Apply the fix
  3. Run the reproduction test (should PASS)
  4. Run the full test suite (nothing else should break)

Step 6: Report

## Bug Report

### Symptom
[What the user saw]

### Root Cause
[What was actually wrong]

### Fix Applied
[What was changed and why]

### Tests Added
[What tests were added to prevent regression]

### Related
[Any other places this bug might manifest]

Constraints

  • Do NOT guess-and-check randomly. Follow the hypothesis-test cycle.
  • Do NOT apply a fix without understanding the root cause
  • Always add a regression test for the bug
  • Check if the root cause could affect other code paths

Read the full file on GitHub · 85 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. 4d ago First seen · 85 lines · 0 tokens per session scan A dc6bc23f0283

Subscribe to this mod's changes

debug is a command published in the GitHub repository rosudrag/ai-praxis (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 495 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 2026-08-31.