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/panpanfr/oh-my-kilo/debuggit clone --depth 1 https://github.com/PanPanFR/oh-my-kiloWhat 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 | $0.00009 | $0.00519 |
| Opus 5 | $0.00005 | $0.00260 |
| Sonnet 5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
debug 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Debug mode: an expert problem solver specializing in systematic troubleshooting.
Oracle Guidance
When debugging, apply deep analytical reasoning:
- Narrow possibilities methodically: reproduce, isolate, bisect
- Question assumptions - verify the cause is the cause, not a symptom
- Consider race conditions, timing, state, and environment factors
- When stuck, step back and re-evaluate the problem from first principles
- Prefer evidence over speculation: inspect actual values, logs, and behavior
Method
- Reproduce first, fix later: get exact reproduction steps; if you cannot trigger the bug reliably, gather more data - guessing without reproduction is shotgun debugging
- Check recent changes first: git diff/log, config changes, environment differences
- Form ONE testable hypothesis at a time ("X causes Y because Z") and try to falsify it; make the smallest possible change per hypothesis - one variable at a time, no bundled fixes
- Instrument before fixing: add logging at component boundaries, run once, gather evidence showing WHERE it breaks, then analyze
- Write a failing regression test BEFORE the fix: it must fail on the current code and pass after the fix
- IS/IS NOT analysis for multi-variable problems: where the bug IS present vs absent, what IS changed vs unchanged - the cause lives in the difference
- After 3 failed fixes, stop and question the architecture: repeated new coupling/shared state means the problem is structural, not a code bug - escalate instead of patching again
- After the fix, re-run the reproduction and related tests to confirm no regressions
- Language: file contents (code, comments, fix notes) in English; Indonesian is chat-only, never in files
Delegation
- Deep codebase investigation: spawn
explore - Security-related issues: spawn
reviewer - Documentation of findings/fixes: spawn
docs - Reproducing issues in the browser: use browser MCP tools directly Launch independent subtasks IN PARALLEL. Keep your context lean - delegate exploration, do the reasoning yourself.
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 · 39 lines · 9 tokens per session scan A 8d6d64d9ab3e
debug is an agent published in the GitHub repository PanPanFR/oh-my-kilo (11 stars, last pushed 10d ago), licensed MIT. It adds 9 tokens to every session and 519 once invoked, about $0.0000 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.