debug-with-file

A guided debugging command that investigates a bug, records changing explanations, and adds temporary logging to observe program state.

In plain words
What is it for?
Use it to investigate an error message, stack trace, or bug; document the investigation; apply a fix; verify the result; and remove temporary debugging logs.
Why use it?
It keeps evidence, rejected ideas, and conclusions in one place, helping prevent repeated investigation or fixes based on a misunderstanding.

Command for Claude Code

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/catlog22/claude-code-workflow/debug-with-file
Clone the repo
git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,114 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 $0.00019 $0.04114
Opus 5 $0.00010 $0.02057
Sonnet 5 $0.00004 $0.00823
Haiku 4.5 $0.00002 $0.00411

Measured 2d ago against content hash 10f074762c43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-with-file 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.

.claude/commands/workflow/debug-with-file.md · 657 lines

How it starts

The opening of the file, as written. The whole thing — 657 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Mode

When --yes or -y: Auto-confirm all decisions (hypotheses, fixes, iteration), use recommended settings.

Workflow Debug-With-File Command (/workflow:debug-with-file)

Overview

Enhanced evidence-based debugging with documented exploration process. Records understanding evolution, consolidates insights, and uses Gemini to correct misunderstandings.

Core workflow: Explore → Document → Log → Analyze → Correct Understanding → Fix → Verify

Scope: Adds temporary debug logging to observe program state; cleans up all instrumentation after resolution. Does NOT execute code injection, security testing, or modify program behavior.

Key enhancements over /workflow:debug:

  • understanding.md: Timeline of exploration and learning
  • Gemini-assisted correction: Validates and corrects hypotheses
  • Consolidation: Simplifies proven-wrong understanding to avoid clutter
  • Learning retention: Preserves what was learned, even from failed attempts

Usage

/workflow:debug-with-file <BUG_DESCRIPTION>

# Arguments
<bug-description>          Bug description, error message, or stack trace (required)

Execution Process

Session Detection:
   ├─ Check if debug session exists for this bug
   ├─ EXISTS + understanding.md exists → Continue mode
   └─ NOT_FOUND → Explore mode

Explore Mode:
   ├─ Locate error source in codebase
   ├─ Document initial understanding in understanding.md
   ├─ Generate testable hypotheses with Gemini validation
   ├─ Add NDJSON debug logging statements
   └─ Output: Hypothesis list + await user reproduction

Analyze Mode:
   ├─ Parse debug.log, validate each hypothesis
   ├─ Use Gemini to analyze evidence and correct understanding
   ├─ Update understanding.md with:
   │   ├─ New evidence
   │   ├─ Corrected misunderstandings (strikethrough + correction)
   │   └─ Consolidated current understanding
   └─ Decision:
       ├─ Confirmed → Fix root cause
       ├─ Inconclusive → Add more logging, iterate
       └─ All rejected → Gemini-assisted new hypotheses

Fix & Cleanup:
   ├─ Apply fix based on confirmed hypothesis
   ├─ User verifies
   ├─ Document final understanding + lessons learned
   ├─ Remove debug instrumentation
   └─ If not fixed → Return to Analyze mode

Read the full file on GitHub · 657 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 · 657 lines · 19 tokens per session scan A 10f074762c43

Subscribe to this mod's changes

debug-with-file is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 4,114 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 2026-08-30.