品質ゲート、評価、リカバリーコントロールを備えた継続的な自律エージェントループのパターン。
Scanned 9/12/2026
Install to Claude Code
npx -y skills add thedixitjain/the-mega-skill-library --skill continuous-agent-loop --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Continuous Agent Loop?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/thedixitjain-continuous-agent-loop)More formats (shields.io, HTML) on the badges page.
---
name: continuous-agent-loop
description: "品質ゲート、評価、リカバリーコントロールを備えた継続的な自律エージェントループのパターン。"
category: ai-agents-and-harness
source_repo: affaan-m/ECC
source_path: "docs/ja-JP/skills/continuous-agent-loop/SKILL.md"
source_url: https://github.com/affaan-m/ECC/blob/HEAD/docs/ja-JP/skills/continuous-agent-loop/SKILL.md
---
# 継続的エージェントループ
これはv1.8+の標準ループスキル名です。1リリースの間、`autonomous-loops`との互換性を保ちながら置き換えます。
## ループ選択フロー
```text
Start
|
+-- Need strict CI/PR control? -- yes --> continuous-pr
|
+-- Need RFC decomposition? -- yes --> rfc-dag
|
+-- Need exploratory parallel generation? -- yes --> infinite
|
+-- default --> sequential
```
## 組み合わせパターン
推奨される本番スタック:
1. RFC分解(`ralphinho-rfc-pipeline`)
2. 品質ゲート(`plankton-code-quality` + `/quality-gate`)
3. 評価ループ(`eval-harness`)
4. セッション永続化(`nanoclaw-repl`)
## 失敗モード
- 測定可能な進捗なしのループチャーン
- 同じ根本原因での繰り返しリトライ
- マージキューの停止
- 無制限のエスカレーションによるコストドリフト
## リカバリー
- ループを凍結する
- `/harness-audit`を実行する
- スコープを失敗ユニットに縮小する
- 明示的な受け入れ基準でリプレイする
---
**Source:** [`affaan-m/ECC`](https://github.com/affaan-m/ECC) → `docs/ja-JP/skills/continuous-agent-loop/SKILL.md`
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling