auto-implement

auto-implement is a skill for Claude Code from careerchain-ys/stdd. It costs 134 tokens per session (3,119 once invoked), scanned A, original, Apache-2.0.

An automated workflow that takes a software task from an issue, document, URL, or plain description through clarification, specifications, planning, coding, testing, review, design updates, and pull-request creation.

In plain words
What is it for?
Use it to turn a GitHub issue or other task description into requirements and technical design, then implement, test, review, and prepare the change for a pull request.
Why use it?
It organizes the many stages between an idea and a reviewed code change, especially when the original request is incomplete or unclear.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/create-worktree.sh -b claude/<branch-name> -i <instance-id>.

Good fit Use it to turn a GitHub issue or other task description into requirements and technical design, then implement, test, review, and prepare the change for a pull request.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/careerchain-ys/stdd
agentmods
npx agentmods add skills/careerchain-ys/stdd/auto-implement

Made for: Claude Code.

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 auto-implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/careerchain-ys/stdd/auto-implement/github.svg)](https://agentmods.dev/skills/careerchain-ys/stdd/auto-implement)
Your own site
<a href="https://agentmods.dev/skills/careerchain-ys/stdd/auto-implement"><img src="https://agentmods.dev/badge/skills/careerchain-ys/stdd/auto-implement/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.

agentmods 80×15 button for auto-implement

Your own site · 80×15
<a href="https://agentmods.dev/skills/careerchain-ys/stdd/auto-implement"><img src="https://agentmods.dev/badge/skills/careerchain-ys/stdd/auto-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,119 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.03119
Opus 5.5 $0.00054 $0.01248
Sonnet 5.5 $0.00027 $0.00624
Haiku 4.5 $0.00013 $0.00312

Measured 2mo ago against content hash aa8cc99589ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-implement 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 2mo 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.

.agents/skills/auto-implement/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

自動実装オーケストレーション

実装したい課題(GitHub issue / 自由記述の要望 / 既存ドキュメント / Slack・Notion などの参照 / URL)を受け取り、ヒアリングで対象を確定したうえで、Spec作成→実装→QA→コードレビュー→PR作成までを自動で実行するオーケストレーションスキル。

入力は GitHub issue に限らない。 issue 番号があればそれを使うが、無くてもよい。入力が無い / 曖昧な場合は Step 1 のヒアリングで対象を具体化してから進める。

引数

形式: [<入力>] [--mode <full|spec-only|impl-only|quick>]

  • <入力>(任意): #<issue番号> / issue URL / 自由記述のタスク説明 / ドキュメントのパス・URL のいずれでも可。省略可能。
  • --mode(任意): 実行モード。

Step 1: 入力のヒアリングと確定

auto-implement の対象(実装したい issue / 課題 / 要望)を確定するフェーズ。いきなり実装に進まず、まずここで対象を明確にする。

  1. 初期入力の取り込み: 引数で入力が与えられていれば、その種別を判定する。
    • #<番号> または issue URL → GitHub issue(Step 2 で gh 取得)
    • 自由記述のテキスト → タスク記述としてそのまま扱う
    • ファイルパス / ドキュメント URL → 読み込んでタスク記述の素材にする
  2. ヒアリング: 入力が無い、または上記だけでは auto-implement を始めるのに不十分な場合は、ユーザーに以下を確認する(AskUserQuestion 等で簡潔に):
    • 何を実装したいか(目的・背景・解決したい課題)
    • 入力ソース(GitHub issue / 自由記述 / 既存ドキュメント / その他)— issue なら番号を聞く
    • スコープ・制約(対象アプリ / 機能、含める・含めないもの、既知の制約)
  3. 確定: 課題内容が「Spec 作成に着手できる程度」に具体化できたら、要点をユーザーに復唱して確認を取る。曖昧なまま先に進まない。

このヒアリングの結果(タスクのタイトル相当・本文相当・スコープ)を、以降のフェーズの**入力(タスク記述)**として扱う。

Step 2: 入力情報の取得・正規化

Step 1 で確定した入力を、以降のフェーズが扱えるタスク記述(タイトル相当・本文相当・補足)に正規化する。

  • GitHub issue の場合: GitHub MCP tools または gh issue view で取得する。
    • タイトル / 本文(description) / ラベル / コメント
  • issue 以外の場合(自由記述・ドキュメント等): ヒアリング結果や参照ドキュメントから、タイトル相当・本文相当・スコープを構成する。ラベルは無いものとして扱う。

以降のステップで「issue」と記載がある箇所は、issue 以外の入力ではこの正規化済みタスク記述に読み替える。

Step 3: 実行モード判定

--mode が指定されている場合はそのモードを使用。未指定の場合は以下のロジックで自動判定する(issue 以外の入力では「ラベル」条件は対象外。タイトル・本文の内容で判定する):

条件 モード
(issue の場合)ラベルに bug を含む / 不具合の修正が主目的 impl-only
ラベルに documentation を含む、またはタイトルに「Spec」「リバースエンジニアリング」を含む spec-only
タイトルに「typo」「修正」を含む、または本文が短い(200文字以下) quick
上記いずれにも該当しない full

Read the full file on GitHub · 183 lines

Files

What ships with it

1 file 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. 2mo ago First seen · 183 lines · 134 tokens per session scan A aa8cc99589ba

Subscribe to this mod's changes

auto-implement is a skill published in the GitHub repository careerchain-ys/stdd (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 134 tokens to every session and 3,119 once invoked, about $0.0005 per session on Opus 5.5. 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.