dev-debug

A structured debugging workflow that finds and confirms the root cause before changing code. It moves through reproducing, locating, reducing, fixing, and guarding against the bug.

In plain words
What is it for?
Use it to investigate errors, create a minimal reproduction, inspect related code, apply a targeted fix, and add protection against recurrence.
Why use it?
It reduces trial-and-error fixes that may hide the original problem or introduce new bugs.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/hiepdnh/agentic-development-lifecycle/dev-debug
Any agent
npx skills add hiepdnh/Agentic-Development-Lifecycle --skill dev-debug
Clone the repo
git clone --depth 1 https://github.com/hiepdnh/Agentic-Development-Lifecycle

Made for: Claude Code, Codex.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,108 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.01108
Opus 5 $0.00036 $0.00554
Sonnet 5 $0.00015 $0.00222
Haiku 4.5 $0.00007 $0.00111

Measured 2d ago against content hash 8d25b1294f4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-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.

.claude/skills/dev-debug/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: /dev-debug

Role: Developer
Mục đích: Systematic debugging — tìm root cause trước khi fix. Tránh "fix ngẫu nhiên cho đến khi hết lỗi".


Nguyên tắc cốt lõi

Không bao giờ touch code trước khi có minimal reproduction.
Fix sai root cause = tạo thêm bugs.

Quy trình 5 bước

Bước 1 — Reproduce

## Tôi sẽ giúp debug vấn đề này.

Trước tiên:

| # | Câu hỏi | Lựa chọn |
|---|---------|---------|
| 1 | Mô tả lỗi: gì xảy ra vs gì mong đợi? | _(điền vào)_ |
| 2 | Steps to reproduce | _(điền vào — dù rough cũng được)_ |
| 3 | Lỗi này mới xuất hiện hay luôn có? | A: Mới xuất hiện — sau thay đổi: ___ / B: Luôn có / C: Không chắc / D: Khác: ___ |
| 4 | Error message / stack trace | _(paste vào đây nếu có)_ |

Ask First Gate: Nếu lỗi xảy ra trên production với user thật → báo ngay cho team trước khi debug. Xem thêm assets/ask-first-gates.md.

Bước 2 — Localize

Spawn subagent để đọc code liên quan (read-only), dùng lại agents/code-scout.md:

Agent(
  description: "Find code related to reported bug",
  prompt: "Tìm code xử lý hành vi mô tả bên dưới. Trả về JSON theo agents/code-scout.md spec — relevant_files (file:line + lý do suspect) và entry_points (entry point đến điểm có thể fail). Chỉ đọc, không sửa gì.\n\nTASK SUMMARY: [mô tả lỗi + steps to reproduce + error message từ Bước 1]\nTECH STACK: [language, framework, folder structure nếu biết]",
  model: "haiku"
)

Subagent trả về relevant_files (file:line + lý do suspect) và entry_points — dùng để trình bày bên dưới.

Trình bày:

## Tôi xác định vùng code có thể là nguồn lỗi:

1. [file:line] — [lý do suspect]
2. [file:line] — [lý do suspect]

Hypothesis:
- H1: [Giả thuyết 1 về nguyên nhân]
- H2: [Giả thuyết 2]

Tôi sẽ kiểm tra H1 trước vì [lý do].
Bạn có thêm hypothesis nào dựa trên context bạn biết không?

Bước 3 — Reduce

Tạo minimal reproduction — code nhỏ nhất có thể trigger lỗi.

## Minimal reproduction:

[Code snippet hoặc steps tối thiểu]

Lỗi có reproduce với code này không?
(Nếu không → vấn đề nằm ở interaction với phần khác, không phải đây)

Read the full file on GitHub · 137 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 137 lines · 73 tokens per session scan A 8d25b1294f4e

Subscribe to this mod's changes

dev-debug is a skill published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 1,108 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens