Feature: skill to autonomously drive feature implementation from work items via sub-agents
メンテナーはふだん 1 日以内に返信
まだ誰も着手していません。
評価
調査の方向性
Start by reading the existing skills under han-coding/skills/, especially tdd and code-review, then trace plan-work-items, work-items.md, plan-implementation, and agent dispatch in han-core/agents/. Check how workflows and sub-agents are currently invoked. Done means a documented skill can process work items, invoke development and review, honor HITL tasks, and pause on unresolved blockers.
索引モデルが issue の本文から書いたものです。
説明
Summary
A skill that, given a set of work items, drives feature implementation end-to-end — offloading development and code review to sub-agents — and only pauses for input on human-in-the-loop (HITL) tasks or on blockers that can't be resolved without changing the planned spec/architecture.
Motivation (current flow)
I use han to implement small-to-medium features on a pet project. After the planning phase, han produces an implementation plan, but the implementation itself is manual: for each work item I hand-invoke tdd and then code-review.
That per-item loop is great for work units with high uncertainty, but it becomes tedious for long features that already have a good specification. Running tdd and code-review also consumes a lot of context, so I have to compact the session every few work items, which costs extra time.
Proposed behavior
A new skill that takes work items and drives implementation, offloading the heavy lifting (development via tdd, review via code-review) to sub-agents, pausing only for:
- HITL tasks, and
- blockers that require my explicit decision because they can't be resolved without changing the planned feature spec, architecture, or similar.
Prior art (I've reproduced this manually)
I've already reproduced the flow by instructing Claude to implement a set of work units while passing development and code review onto sub-agents. Two things were needed to make it reliable:
- I had to explicitly pass the skill names to the sub-agents, otherwise they wouldn't invoke
tdd/code-review. - I had to give explicit per-task model instructions (in the end I just told it to use opus for everything).
Design direction
Where I have a direction, and where I don't:
- How work items are supplied — from
plan-work-items. In practice I commit the feature spec and instruct the agents to read it before proceeding. - Per-work-item completion gate — tests green and
code-reviewreports no findings at severity medium or above. The severity threshold should probably be configurable; pinning down the exact mechanism needs a closer look at thecode-reviewskill. - How a HITL task is recognized —
plan-work-itemsalready classifies each task as AFK or HITL; the skill keys off that. - How a "blocker requiring an explicit decision" is detected — genuinely open. We'll need to try different approaches and see what works.
- Model-selection policy — to be decided later. Likely an optional skill input with an adaptive default. Worth researching the
superpowersskill pack, which does a fairly good job of this. - Failure handling when a sub-agent's
tdd/code-reviewfails or returns findings — either escalate to me, or run atdd→code-review→tdd→ … loop with a hard cap on the iteration count.
Implementation considerations
- Claude workflows could orchestrate this automatically. Caveat: agents spawned via workflows can't use the
Agenttool, so skills that themselves rely on sub-agents (notablycode-review) will need additional consideration.
Suspected areas
- New skill placement: likely a coding-time skill under
han-coding/skills/(alongsidetdd/code-review), or an orchestration skill bridging planning and coding. - The
tddandcode-reviewskills (han-coding/skills/) — the per-item steps dispatched to sub-agents. - The work-item pipeline:
plan-work-items/work-items.mdandplan-implementation(han-planning/skills/) — the upstream that feeds this skill. - Sub-agent dispatch and the agent roster (
han-core/agents/) — including the per-task model selection and explicit-skill-name concerns above.
Ask
Would you be interested in a PR contributing such a skill?
- 主要言語
- Shell
- スター
- 320
- フォーク
- 25
- 平均マージ
- 4日 17時間
- マージ済み PR（30日）
- 8
環境構築
- Dockerfile・Docker Compose ファイルなし
- プルリクエストのテンプレートあり
- コントリビューションガイドを読む
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
testdouble/han のほかの issue
-
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
testdouble/han#215 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
-
難易度 5/5 1週間以上 初心者へのやさしさ 45/100
testdouble/han#217 · コメント 1 件 · リアクション 1 件 ·
メンテナーはふだん 1 日以内に返信
-
難易度 5/5 1週間以上 初心者へのやさしさ 35/100
testdouble/han#216 · コメント 1 件 · リアクション 1 件 ·
メンテナーはふだん 1 日以内に返信
-
Consolidate config loading; the inline half of the data-fetch prohibition is unevidenced対応中かも @taminomara が 3 日前に担当しました。 オープン
難易度 5/5 1週間以上 初心者へのやさしさ 45/100
testdouble/han#203 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
-
難易度 4/5 3〜5日 初心者へのやさしさ 45/100
testdouble/han#202 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
似ている issue
-
lesson-submission pending-review
難易度 1/5 1時間未満 初心者へのやさしさ 74/100
Ikalus1988/MisakaNet#3899 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
awsdocs/amazon-eks-user-guide#1257 ·
-
deep-dive-feedback
難易度 2/5 1〜3時間 初心者へのやさしさ 78/100
aws-samples/sample-apex-skills#292 ·
メンテナーはふだん 1 日以内に返信
-
fm-spawn: bash 5.2 patsub_replacement turns '&' in a home or project path into the placeholder textオープン
難易度 2/5 1〜3時間 初心者へのやさしさ 77/100
kunchenguid/firstmate#7786 ·
メンテナーはふだん 1 日以内に返信
-
TLS guide repeats certs/ in the certificate directory対応中かも @maheshrijal が今日担当しました。 オープン
難易度 1/5 1時間未満 初心者へのやさしさ 92/100
prometheus/docs#3156 ·
メンテナーはふだん 2 日以内に返信