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.
npx agentmods add skills/eaglesakura/agent-skills/coding.loopnpx skills add eaglesakura/agent-skills --skill coding.loopgit clone --depth 1 https://github.com/eaglesakura/agent-skillsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00182 | $0.05298 |
| Opus 5 | $0.00091 | $0.02649 |
| Sonnet 5 | $0.00036 | $0.01060 |
| Haiku 4.5 | $0.00018 | $0.00530 |
Grade A, and why
coding.loop 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding / ループエンジニアリング
要件定義済み計画を起点に、完了条件を満たすまで /coding.design と /coding.execute(各ステップ後は必ず /coding.comment)を自律反復する。
Coding-Commands のステップ2〜3を外側ループで束ねる。ステップ1(/coding.requirement)は前提として完了済みであること。
正本はこの SKILL のみ(同名 Prompt は置かない)。
本 SKILL 実行中は、単発 /coding.design 末尾の「ユーザー承認待ち」で止まらず、ゲート(DO NOT 残ゼロ・完了条件・タイムアウト)に従って execute / 次ループへ進む。
要件定義済み計画を進める過程で、追加の要件・実装詳細・解釈の分岐が出た場合は、次節の優先度に従って解決する(推測のまま進めない)。
未決の追加要件・実装詳細の解決優先度
適用対象: ループ中(分割計画の用意・design・レビュー・execute)に現れた、計画に足りない追加要件や実装詳細。
適用しない: 完了条件そのものが不明な場合(事前チェックの緊急停止)、および /coding.requirement のやり直し。
次の順で試し、上で決まれば下へ進まない。
flowchart TD
Gap["追加要件・実装詳細の未決"] --> P1{"1. SKILL / ドキュメントで<br/>解決できるか"}
P1 -->|はい| Apply1["その規約・手順に従う"]
P1 -->|いいえ| P2{"2. 既存コードの慣習・<br/>隣接実装で解決できるか"}
P2 -->|はい| Apply2["既存に揃える"]
P2 -->|いいえ| P3["3. 異なる Model の<br/>Sub Agent 3体で合議"]
P3 --> Decide["多数意見を採用し<br/>分割計画へ明記"]
1. SKILL およびドキュメントに従う
- 本 SKILL、
engineer-software-design、agent-job-description、{assets}/coding/* - リポジトリの
docs/、レイヤー規約、Coding-Commands 関連文書、関連 SKILL の DO / DO NOT - ここで一意に決まるなら、その決定を分割計画に書いて続行する
2. 既存コードに従う
- 同レイヤー・隣接 feature・同種の既存実装・テストの書き方を正とする
- 「プロジェクトで既にやっているやり方」を優先し、新規パターンを発明しない
- 根拠となるファイルパスを分割計画に残す
3. 異なる Model の Sub Agent 3体で合議する
1 と 2 で決まらないときだけ行う。/coding.design / /coding.execute の通常レビュー経路とは別の、未決解消用の例外である。
- 未決点・制約・候補を短く整理した同一プロンプトで、互いに異なる model の Sub Agent を 3つ並列起動する
- model はセッションで利用可能なスラッグから選ぶ(例: 異なる提供元・系統を混ぜる)
- 3体とも同じ model にしない
- 各 Agent に、結論・根拠・却下した案を返させる(実装差分の本番適用はさせない。助言のみ)
- 親 Agent が合議する
- 2体以上が一致 → その案を採用
- 3者ばらばら → 既存コードへの影響が小さい案、またはドキュメントに近い案を選び、却下理由を計画に残す
- 採用結果を
{stem}_{N}.mdに明記してから design / execute を続ける - 合議でも完了条件自体が割れ、検証不能になった場合のみ緊急停止(完了条件不明)する
呼び出し形式(必須)
/loop /coding.loop {要件定義済み計画} {完了条件・任意のタイムアウト等}
/loopが先、続けて SKILL 名coding.loop- skill 単独や形式不一致では 起動しない
いつ使うか / 使わないか
使う:
/loop /coding.loop …で始まる指示のみ
使わない:
- skill 単独の呼び出し(
/loop無し) - 単発の
/coding.design//coding.execute /coding.requirement未完了、または要件計画が無い- 完了条件がプロンプトにも計画にも無い(→ 事前チェックで緊急停止)
- Coding-Commands 外の
/loop(例: ライブラリ更新だけ)
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.
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.
- yesterday First seen · 351 lines · 182 tokens per session scan A d8aace4e690d
coding.loop is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 182 tokens to every session and 5,298 once invoked, about $0.0009 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…