debug-tool

A command for investigating a failed tool call, applying a known fix when available, and saving new fixes.

In plain words
What is it for?
Checking known issues, analyzing unfamiliar tool failures, and documenting fixes for future runs.
Why use it?
It provides a defined path from an error to diagnosis and a reusable record of the solution.

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/dmzoneill/redhat-ai-workflow/debug-tool
Clone the repo
git clone --depth 1 https://github.com/dmzoneill/redhat-ai-workflow
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 550 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 $0.00550
Opus 5 $0.00000 $0.00275
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 2d ago against content hash ea2741696682, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-tool 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.

docs/commands/debug-tool.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/debug-tool

When a tool fails, use auto-debug to fix it AND save the learning.

Overview

When a tool fails, use auto-debug to fix it AND save the learning.

Arguments

No arguments required.

Usage

Examples

check_known_issues(tool_name="bonfire_deploy")
check_known_issues(error_text="manifest unknown")
❌ Failed to deploy
💡 To auto-fix: debug_tool('bonfire_deploy_aa')
debug_tool("bonfire_deploy_aa", "error message here")

Process Flow

flowchart TD
    START([Start]) --> PROCESS[Process Command]
    PROCESS --> END([Complete])

    style START fill:#6366f1,stroke:#4f46e5,color:#fff
    style END fill:#10b981,stroke:#059669,color:#fff
```text

## Details

## Step 1: Check Known Issues First
```text
check_known_issues(tool_name="bonfire_deploy")
check_known_issues(error_text="manifest unknown")
```text

If a fix is known, apply it immediately!

## Step 2: If Unknown, Debug the Tool

When you see a failure like:
```text
❌ Failed to deploy
💡 To auto-fix: debug_tool('bonfire_deploy_aa')
```text

Call debug_tool:
```text
debug_tool("bonfire_deploy_aa", "error message here")
```text

I will:
1. Load the tool's source code
2. Analyze the error against the code
3. Propose a specific fix
4. Ask for confirmation before applying
5. Commit the fix and retry

## Step 3: Save the Learning!

After the fix works:
```text
learn_tool_fix(
    tool_name="bonfire_deploy",
    error_pattern="manifest unknown",
    root_cause="Short SHA doesn't exist",
    fix_description="Use full 40-char SHA"
)
```text

This creates a **learning loop** - next time, `check_known_issues()` will find the fix!

## Common fixable bugs:
- Missing `--force` flag (TTY errors)
- Wrong CLI syntax
- Auth not passed correctly
- Image tag format issues

## The Learning Loop
```text
Fail → check_known_issues() → debug_tool() → fix → learn_tool_fix() → ✓
           ↑                                              |
           └──────────── remembered forever ←─────────────┘

Read the full file on GitHub · 103 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 · 103 lines · 0 tokens per session scan A ea2741696682

Subscribe to this mod's changes

debug-tool is a command published in the GitHub repository dmzoneill/redhat-ai-workflow (5 stars, last pushed 23d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 550 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.