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 skills add wewpellex21/code-sensei --skill debugginggit clone --depth 1 https://github.com/wewpellex21/code-senseiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wewpellex21/code-sensei/debugging)<a href="https://agentmods.dev/skills/wewpellex21/code-sensei/debugging"><img src="https://agentmods.dev/badge/skills/wewpellex21/code-sensei/debugging/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wewpellex21/code-sensei/debugging"><img src="https://agentmods.dev/badge/skills/wewpellex21/code-sensei/debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00710 |
| Opus 5.5 | $0.00014 | $0.00284 |
| Sonnet 5.5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
debugging 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 1mo 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.
This is a copy
100% identical to debugging — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging — CodeSensei Teaching Module
What is Debugging?
- Analogy: Debugging is detective work. Something isn't working, and you need to find out why. Every error message is a clue.
- Key insight: Errors are NOT failures. They're the computer telling you exactly what went wrong and where. Learning to read errors is the single most valuable programming skill.
How to Read Error Messages
Teach users to look for these three things in EVERY error:
- What happened — the error type (TypeError, SyntaxError, 404, etc.)
- Where it happened — the file name and line number
- Why it happened — the description message
Example:
TypeError: Cannot read property 'name' of undefined
at UserCard (src/components/UserCard.jsx:12)
Translation: "On line 12 of UserCard.jsx, you tried to get .name from something that doesn't exist yet."
Common Error Types (teach as encountered)
Frontend Errors
- "Cannot read property X of undefined" — you're trying to use data that hasn't loaded yet. Like trying to read a book that hasn't been delivered.
- "X is not defined" — you're using a variable/function that doesn't exist. Likely a typo or missing import.
- "X is not a function" — you're trying to call something as a function, but it's not one.
- White screen of death — usually a component crashed during rendering. Check the browser console.
Backend Errors
- 404 Not Found — the URL/route doesn't exist. Like going to a room number that doesn't exist in the building.
- 500 Internal Server Error — something broke on the server. Check the server logs.
- 401 Unauthorized — you're not logged in (or your token expired).
- 403 Forbidden — you're logged in but don't have permission.
- CORS error — your frontend is trying to talk to a backend that doesn't trust it. Like calling a secure building and not being on the approved list.
Database Errors
- "relation X does not exist" — the table hasn't been created yet. Run your migrations.
- "unique constraint violation" — you're trying to add a duplicate entry (like two users with the same email).
- "null value in column X violates not-null constraint" — you forgot to include a required field.
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.
- 1mo ago First seen · 63 lines · 36 tokens per session scan A 7812de715f7c
debugging is a skill published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 710 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to debugging, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
perf-profiler
Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.
perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.
dead-code
Identify unused code (functions, imports, exports, variables, types, classes) and propose cleanup. Use this skill when the user says "find dead code", "unused code", "clean up unused", "code hygiene", "find unused imports", "what can I delete", or any variation of wanting to identify and remove code that is no longer…
question
Answer a question about how things are right now — this codebase, its history, its behavior, a library, an error. Investigates and answers with evidence. Changes nothing, ever.