dev-autopilot

dev-autopilot is a skill for Claude Code, Codex from hiepdnh/Agentic-Development-Lifecycle. It costs 65 tokens per session (1,781 once invoked), scanned A, original, MIT.

An opt-in workflow for letting an AI coding agent carry a task through planning, incremental coding, checks, independent reviews, and handoff. It asks for permission and stops when a risky decision needs human approval.

In plain words
What is it for?
Use it to run an approved coding task from start to finish, validate the result, get two independent evaluations, and prepare evidence for handoff.
Why use it?
It reduces the need to confirm every small file change while keeping checks and approval points for higher-risk work.

Skill for Claude CodeCodex

Part of the agentic-development-lifecycle plugin — 35 skills shipped together

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

Made for: Claude Code, Codex.

Or install agentic-development-lifecycle, the plugin that ships this one along with the rest of its 35 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.

agentmods badge for dev-autopilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/hiepdnh/agentic-development-lifecycle/dev-autopilot.svg)](https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/dev-autopilot)
Your own site
<a href="https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/dev-autopilot"><img src="https://agentmods.dev/badge/skills/hiepdnh/agentic-development-lifecycle/dev-autopilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,781 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 $0.00065 $0.01781
Opus 5 $0.00032 $0.00890
Sonnet 5 $0.00013 $0.00356
Haiku 4.5 $0.00006 $0.00178

Measured 4d ago against content hash 688a40f7ab98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-autopilot 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 4d 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-autopilot/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: /dev-autopilot

Role: Autonomous Developer Mục đích: Autonomy lane opt-in cho task đã risk-classify — initializer, incremental implementation loop, 2 evaluator độc lập, và evidence-based handoff, không cần confirm sau mỗi file như /dev-implement.


Quan trọng

Đây là lane opt-in, không thay thế lane thủ công mặc định /dev-analyze/dev-implement/dev-review/dev-pr. Mọi skill khác của framework vẫn giữ hard-stop sau mỗi bước; autopilot chỉ áp dụng cho task đã được user cấp quyền tự động rõ ràng. Đọc docs/agent-harness.md và tuân thủ như operating contract trong suốt task.


Hướng dẫn thực hiện

Bước 0 — Risk + autonomy gate

Classify task theo docs/risk-classifier.md: xác định input type, R-01..R-10 nào áp dụng, và lane tiny/normal/high-risk. Nếu gặp Hard Trigger → dùng đúng format ⚠️ Ask First Gate trong assets/ask-first-gates.md và dừng chờ confirm senior trước khi tiếp tục.

Dùng AskUserQuestion xác nhận một lần trước khi chạy: Task ID, objective/AC, base branch hoặc worktree, lệnh được phép chạy, iteration budget (mặc định 3), và quyền mở PR. Approval cho high-risk không loại bỏ evaluator loop bắt buộc ở Bước 3.

Chờ confirm trước khi sửa file.


Bước 1 — Initializer và durable state

  1. Đọc docs/tasks/[TASK-ID]/analysis.md nếu đã tồn tại (tiny lane có thể bỏ qua — ghi plan trực tiếp vào state).
  2. Chuẩn hóa objective thành AC kiểm chứng được.
  3. Tạo docs/tasks/[TASK-ID]/agent-state.md theo template trong docs/agent-harness.md.
  4. Chạy baseline nhỏ nhất có ý nghĩa (build/test hiện có của repo) và ghi command + kết quả trước khi sửa code. Không nhận một lỗi có sẵn là do task nếu chưa có before/after signal.

Baseline fail không giải thích được hoặc requirement conflict → set status: blocked trong agent-state.md và escalate qua AskUserQuestion.


Bước 2 — Incremental implementation loop

Mỗi iteration:

  1. Chọn AC nhỏ nhất chưa hoàn thành, implement một increment nhất quán — cùng nguyên tắc như /dev-implement: không jump ahead, không refactor ngoài scope, không thêm feature ngoài AC.
  2. Chạy deterministic checks hẹp trước (unit test liên quan), checks rộng sau khi increment hoàn tất.
  3. Ghi command, output tóm tắt và giả thuyết tiếp theo vào agent-state.md — mục Decisions (quyết định + lý do), Next steps (bước tiếp cụ thể), Open questions (câu hỏi chưa trả lời).
  4. Nếu cùng một blocker thất bại với hai hypothesis khác nhau, hoặc hết iteration budget → escalate.

Read the full file on GitHub · 128 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. 4d ago First seen · 128 lines · 65 tokens per session scan A 688a40f7ab98

Subscribe to this mod's changes

dev-autopilot is a skill published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 7d ago), licensed MIT. It adds 65 tokens to every session and 1,781 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