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.
npx agentmods add commands/catlog22/claude-code-workflow/debug-with-filegit clone --depth 1 https://github.com/catlog22/Claude-Code-WorkflowWhat 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.
| Model | Per session | Once 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 |
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.
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
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.
- 2d ago First seen · 657 lines · 19 tokens per session scan A 10f074762c43
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.
Other commands, from other repositories
verify-claim
Walk a claim through the SIFT method (Stop, Investigate, Find better coverage, Trace).
beat-brief
Draft a daily beat briefing from the files in sample-docs/.
cross-review
Run GitHub Copilot CLI and OpenAI Codex against the current git diff for cross-model review.
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
whats-next
Show current project status and suggest next steps.
ox-session-pause
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Suspend the current session recording. Local cache continues to receive entries, but the upload at stop time will exclude the suspended range.