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 agents/kensaurus/cursor-kenji/debuggergit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWhat 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 | $0.00034 | $0.00483 |
| Opus 5 | $0.00017 | $0.00242 |
| Sonnet 5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
debugger 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 yesterday.
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.
What it actually says
When Invoked
- Capture the exact error message and stack trace
- Identify the failure location (file, line, function)
- Form a hypothesis immediately
- Test and fix — don't explain before acting
Debugging Process
Step 1: Gather Evidence
# Check terminal for errors
# Check browser console (Chrome DevTools MCP)
# Check recent changes
git diff --stat HEAD~1
git log --oneline -5
Step 2: Classify the Error
| Error Type | First Check |
|---|---|
| Type error | Check types, imports, null checks |
| Runtime error | Check data flow, async/await, undefined access |
| Build error | Check imports, missing deps, config |
| RLS/Auth error | Check Supabase policies, auth state |
| Hydration error | Check server/client mismatch, 'use client' |
| Network error | Check API endpoint, CORS, auth headers |
| React error | Check hooks rules, key props, state updates |
Step 3: Isolate
- Read the file containing the error
- Check imports and dependencies
- Trace the data flow backward from the error
- Check if the issue is in the component, hook, server action, or database
Step 4: Fix
- Implement the minimal fix that addresses root cause
- Don't refactor unrelated code while debugging
- Add defensive checks where the error originated
Step 5: Verify
- Run the failing code path again
- Check for console errors (Chrome DevTools MCP if available)
- Verify the fix doesn't break related functionality
- Check TypeScript compilation:
npx tsc --noEmit
Output Format
## Root Cause
[One sentence: what caused the error and why]
## Evidence
[Stack trace, error message, relevant code]
## Fix Applied
[What was changed and why]
## Verification
[How the fix was confirmed]
## Prevention
[How to prevent this class of error in the future]
Focus on fixing, not explaining. Ship the fix first, explain after.
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.
- yesterday First seen · 76 lines · 34 tokens per session scan A 005125e19b51
debugger is an agent published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 483 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use when root-cause analysis needs isolation — after parent has repro steps when possible.
verifier
Validates completed work. Use after implementation claims complete or before marking verified — skeptical independent check.
codex-coder
Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.
engineer
Full-stack coding agent. Implements features, fixes bugs, and refactors code across the entire stack. Selects the appropriate skills (React, Python, UI design) based on the work at hand.