dev-pr

A workflow that creates a structured pull request description from code changes and task documents. A pull request is a proposed change submitted for review before it is merged into the project.

In plain words
What is it for?
Use it to prepare pull request text, link task documentation, verify requirement coverage, and check for sensitive changes before submission.
Why use it?
It checks that the required review has passed and that the pull request explains what changed and how it meets the task requirements.

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

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,437 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 $0.00062 $0.01437
Opus 5 $0.00031 $0.00718
Sonnet 5 $0.00012 $0.00287
Haiku 4.5 $0.00006 $0.00144

Measured 3d ago against content hash 4746567b1954, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-pr 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 3d 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-pr/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: /dev-pr

Role: Developer
Mục đích: Tạo PR description chuẩn từ code changes, link đến task docs và cập nhật baseline.


Ask First Gates (dừng lại trước khi tạo PR nếu có)

Danh sách đầy đủ + lý do: assets/ask-first-gates.md

Nếu PR chứa bất kỳ thay đổi nhạy cảm nào trong danh sách trên → flag rõ trong Gate 2 và chờ confirm senior.


Hướng dẫn thực hiện

Bước 0 — Gate: Kiểm tra review

Tìm docs/tasks/[TASK-ID]/review-log-R[N].md với số N cao nhất (round gần nhất — /dev-review luôn ghi file này bất kể verdict). Nếu tồn tại, đọc Meta.verdict:

  • approve hoặc approve-with-fixes → review đã pass, tiếp tục Bước 1
  • request-changes → dừng, báo user: còn B-xx blocking chưa fix trong review log — chạy lại /dev-review sau khi fix, không tạo PR khi verdict round gần nhất là request-changes

Nếu KHÔNG tìm thấy file review-log-R*.md nào (chưa từng chạy /dev-review) → dùng AskUserQuestion:

  • Câu hỏi: /dev-review đã chạy và Approve chưa?
  • Options: Đã approve — tiếp tục / Chưa chạy — chạy /dev-review trước

Nếu user chọn chưa → dừng, hướng dẫn chạy /dev-review trước.

Chờ confirm.


Bước 1 — Đọc context

Xác định base branch theo thứ tự: user cung cấp trong lệnh → git remote show origin → hỏi user.

Spawn subagent để đọc:

  • git diff <BASE_BRANCH>..HEAD — những gì thay đổi
  • docs/tasks/[TASK-ID]/analysis.md — phương án đã chọn
  • docs/tasks/[TASK-ID]/requirements.md — AC cần verify
  • docs/tasks/[TASK-ID]/verification.md — kết quả self-test (nếu tồn tại)
Agent(
  description: "Read git diff and map changes to AC coverage",
  prompt: "Read the git diff and spec, return AC coverage per agents/diff-reader.md spec.\n\nGIT DIFF:\n[git diff <BASE_BRANCH>..HEAD]\n\nBASE_BRANCH: <tên branch đã xác định>\n\nSPEC PATH: docs/tasks/[TASK-ID]/requirements.md\n\nBASELINE DOCS TO CHECK: [list relevant docs/screens/ and docs/api/ files]",
  model: "haiku"
)

Subagent trả về: summary of changes, files changed, AC coverage, test results (nếu có).

Read the full file on GitHub · 138 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. 3d ago First seen · 138 lines · 62 tokens per session scan A 4746567b1954

Subscribe to this mod's changes

dev-pr is a skill published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 1,437 once invoked, about $0.0003 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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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