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/rafaelkamimura/claude-tools/debug-assistantgit clone --depth 1 https://github.com/rafaelkamimura/claude-toolsWhat 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 | $0.00000 | $0.02374 |
| Opus 5 | $0.00000 | $0.01187 |
| Sonnet 5 | $0.00000 | $0.00475 |
| Haiku 4.5 | $0.00000 | $0.00237 |
Grade A, and why
debug-assistant 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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intelligent Debugging Helper
Advanced debugging assistant that analyzes errors, suggests fixes, traces root causes, and sets up debugging environments.
Purpose
- Analyze error logs and stack traces
- Suggest fixes based on error patterns
- Set up debugging environments
- Generate reproduction steps
- Track down root causes with specialized agents
Workflow
Step 1: Error Input
-
STOP → "How would you like to provide the error?"
1. Paste error message/stack trace 2. Point to log file 3. Describe the issue 4. Run failing command 5. Analyze recent crashes Choose method (1-5): -
Context Gathering
- STOP → "When did this error start? (timestamp/commit/today):"
- STOP → "Is it reproducible? (always/sometimes/once):"
- STOP → "What were you doing when it occurred?:"
Step 2: Error Analysis
-
Parse Error Information
// Extract key information const errorInfo = { type: "TypeError", message: "Cannot read property 'x' of undefined", file: "src/components/UserList.jsx", line: 45, column: 12, stack: [...], timestamp: "2024-01-15T10:30:00Z" }; -
Categorize Error Type
error_categories: - Runtime Errors: - TypeError - ReferenceError - RangeError - Async Errors: - Promise rejection - Callback errors - Race conditions - Network Errors: - Connection refused - Timeout - CORS issues - Build Errors: - Compilation failure - Module not found - Syntax errors -
Deploy Analysis Agents
- debugger: Deep error analysis
- backend-architect: System-level debugging
- test-automator: Create reproduction test
- performance-engineer: Performance-related issues
Step 3: Root Cause Analysis
- Trace Error Source
# Git blame to find when introduced git blame -L 40,50 src/components/UserList.jsx # Check recent changes git log -p --since="2 days ago" src/components/UserList.jsx
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 · 423 lines · 0 tokens per session scan A 9b65ed08bf9c
debug-assistant is a command published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,374 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.