A bug-investigation and bug-fixing workflow with a separate emergency mode for production incidents.

Use it to investigate error messages, inspect relevant code and history, fix ordinary bugs, or handle narrowly scoped production hotfixes.

It helps trace a failure to its underlying cause, reproduce it, and apply checks that show whether the fix works.

debug — Skill for Claude Code by natthasath

Install

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.

Any agent

npx skills add natthasath/natthasath-marketplace --skill debug

Clone the repo

git clone --depth 1 https://github.com/natthasath/natthasath-marketplace

Made for: Claude Code.

Or install projects, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/natthasath/natthasath-marketplace/debug/github.svg)](https://agentmods.dev/skills/natthasath/natthasath-marketplace/debug)

Your own site

<a href="https://agentmods.dev/skills/natthasath/natthasath-marketplace/debug"><img src="https://agentmods.dev/badge/skills/natthasath/natthasath-marketplace/debug/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/natthasath/natthasath-marketplace/debug"><img src="https://agentmods.dev/badge/skills/natthasath/natthasath-marketplace/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 653 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00055	$0.00653
Opus 5	$0.00028	$0.00327
Sonnet 5	$0.00011	$0.00131
Haiku 4.5	$0.00006	$0.00065

Measured 8d ago against content hash 759ae8a9d352, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

debug scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat .claude/config/tech-stack.md 2>/dev/null`

plugins/projects/skills/debug/SKILL.md · 61 lines

What it actually says

!cat .claude/config/tech-stack.md 2>/dev/null

วิเคราะห์และแก้ bug: $ARGUMENTS

อ่าน ../../references/commit-emoji.md เพื่อดู emoji convention ก่อน commit

โหมด --hotfix (Production Emergency)

ถ้า $ARGUMENTS มีคำว่า --hotfix ให้ใช้ขั้นตอนนี้แทน:

เป้าหมาย: แก้เร็วที่สุด กระทบ codebase น้อยที่สุด

Branch — สร้าง hotfix/<slug> จาก main ทันที: git checkout -b hotfix/<slug> main
Fix — แก้เฉพาะจุดที่พัง ห้ามแตะโค้ดอื่น ถ้า fix เกิน ~50 บรรทัดให้หยุดและบอกฉัน
Test — รันเฉพาะ test ที่เกี่ยวข้องโดยตรง ไม่รัน full suite
Commit — 🚑️ fix(<scope>): <สิ่งที่แก้> [hotfix]
ยืนยันก่อนทำ — แสดง branch name + commit message ให้ฉัน approve ก่อนทุกครั้ง

⚠️ ห้าม force push, ห้าม refactor, ห้ามแก้ปัญหาอื่นที่เห็นระหว่างทาง

โหมดปกติ (Careful)

ขั้นที่ 1 — Reproduce ปัญหา:

อธิบายขั้นตอนที่ทำให้เกิด bug
Expected behavior คืออะไร
Actual behavior คืออะไร
Error message (ถ้ามี) คืออะไร

ขั้นที่ 2 — Gather evidence (รัน tools):

ค้นหา error message ใน codebase ด้วย Grep
อ่านไฟล์ที่เกี่ยวข้อง
ดู git log เพื่อหาว่า bug เกิดขึ้นตั้งแต่ commit ไหน: git log --oneline -20

ขั้นที่ 3 — Root cause analysis:

ระบุ root cause (ไม่ใช่แค่ symptom)
อธิบายว่า bug เกิดขึ้นได้อย่างไร
รายงานให้ฉันเห็นก่อนแก้

ขั้นที่ 4 — Fix:

แก้เฉพาะ root cause ไม่แก้ครอบคลุมเกินจำเป็น
เพิ่ม test ที่ reproduce bug ก่อน fix (ควร fail ก่อน แล้วผ่านหลัง fix)
รัน test command (จาก tech-stack.md ด้านบน) หลังแก้

ขั้นที่ 5 — Document:

อธิบายว่าแก้อะไรและทำไม (สำหรับ commit message รูปแบบ 🐛 fix(<scope>): <คำอธิบาย>)

Changes

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.

8d ago First seen · 61 lines · 55 tokens per session scan B 759ae8a9d352

Subscribe to this mod's changes

debug is a skill published in the GitHub repository natthasath/natthasath-marketplace (1 stars, last pushed 8d ago), licensed MIT. It adds 55 tokens to every session and 653 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging claude claude-marketpla claude-plugin claude-skills

operating-cadence

Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…

cbrock84/headcount · 95 tokens

serena

Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.

datit309/supergraph · 40 tokens

diagnose

Structured 6-phase debugging. Build feedback loop first, reproduce deterministically, hypothesize with ranked falsifiable theories, instrument one variable at a time, fix with regression test, cleanup. Use when a bug exists, tests fail unexpectedly, or behavior is wrong and cause is unknown.

datit309/supergraph · 59 tokens

debug