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 skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizengit clone --depth 1 https://github.com/karaage0703/ai-assistant-workspaceWrote 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.
[](https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-xangi-kaizen)<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-xangi-kaizen"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-xangi-kaizen/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.
<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-xangi-kaizen"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-xangi-kaizen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.02556 |
| Opus 5 | $0.00057 | $0.01278 |
| Sonnet 5 | $0.00023 | $0.00511 |
| Haiku 4.5 | $0.00011 | $0.00256 |
Grade A, and why
xs-xangi-kaizen 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xangi-kaizen
xangi 上で起きた事象を「事象整理 → ログ調査 → 真因特定 → 横展開 → 修正・報告」の5フェーズで深掘りし、再発防止までやり切る汎用スキル。
スキルの背景・設計思想・参考文献は README.md を参照。
3原則
- フェーズを飛ばさない — 「事象整理」を飛ばすと検証ポイントを見失う。「横展開」を飛ばすと同じ事故を別箇所で繰り返す
- 想定で終わらせず証拠で詰める — 「たぶん」を提出物にしない。仮説 → 証拠(git log / reflog / mtime / 履歴出力) → 検証
- 真因が特定できるまで実装に進まない — 表面的な対症療法は再発の温床
- コードで推測する前に、事象が出た実際のターンのログを必ず開く — とくに「変な応答が返った」「空だった」「想定と違う出力」系。コードを読んで fallback を見つけると「原因はこれ」と早合点しがちだが、それは「どこで出るか」であって「そのターンで実際に何が起きたか」ではない。先に Phase 2 で対象 bot の session log / tool-trajectory を開き、そのターンの生データを確定してから、コードで「なぜそうなったか」を辿る。
5フェーズのワークフロー
Phase 1: 事象の整理(既知問題チェック含む)
何が起きた / いつ / どこで(チャンネル・対象スキル)。事実を時系列で整理する。
ステップ:
- 引用メッセージ・チャンネル履歴を取得して事象の輪郭をつかむ
xangi tool discord_history --count 30 xangi tool discord_history --channel <ID> --count 50 - 関係するスキル名・cron スケジュール・関連ファイルを箇条書きで把握する
- 過去事例(KEDB = Known Error Database)を必ず確認 —
[NOTES_DIR]の過去 xangi-kaizen ノートを事象キーワードで grep
ヒットした事例は中身を読む。同じパターンなら「対策」「教訓」をそのまま適用できる。未知なら次フェーズへ。# xangi-kaizen タグの全事例 grep -rl '#xangi-kaizen' [NOTES_DIR] | sort # 対象スキル名・キーワードで絞り込み grep -rl '#<対象スキル名>' [NOTES_DIR] grep -rl 'state\|cron\|<キーワード>' [NOTES_DIR]/*xangi-kaizen* 2>/dev/null
Phase 2: ログ調査
複数のソースを横断的に追う。一つの観点で結論を出さない。
ステップ 0(重要): 調査対象 bot の workspace を特定する。 xangi は bot ごとに別 workspace・別プロセスで動く構成を取りうる。複数 bot を運用している場合、手元の workspace だけを見ても対象 bot の事象は写っていないことがある。
# Docker 運用の場合: bot がどのコンテナか確認
docker ps --format '{{.Names}}\t{{.Image}}'
# コンテナの workspace マウント元を確認
docker inspect <container> --format '{{range .Mounts}}{{.Source}} -> {{.Destination}}{{println}}{{end}}' | grep '/workspace'
特定した <bot-workspace> 配下の logs/sessions/ と logs/tool-trajectory/ を見る。環境変数やチャンネル割り当ては各 bot の .env で確認する。
| 観点 | コマンド/対象 |
|---|---|
| state ファイル | [STATE_DIR]/*_state.json、references/*_last_check.json 等の中身と stat -c "%y %n" |
| git 履歴 | git log -p --all -- <path>、git show <commit>:<path> |
| git reflog | git reflog --since=<時刻>(ブランチ切替・rebase・reset の追跡) |
| cron / schedule | xangi tool schedule_list 2>&1 | grep -B2 -A3 <キーワード> |
| セッションログ(生応答) | 対象 bot の <bot-workspace>/logs/sessions/*.jsonl。事象の出たチャンネル ID で grep -rl <channelId> → 該当ファイルの当該ターンを開き、assistant result を確認 |
| tool-trajectory ログ | <bot-workspace>/logs/tool-trajectory/*.jsonl。tool search / loop / drift / stream buffer / cache などのイベントが時系列で残る |
| 該当スクリプト/コード | skills/<name>/scripts/、または対象リポのソース。ログで事象を確定した後に「なぜそうなるか」を辿る |
| 投稿履歴 | xangi tool discord_history --channel <ID> --count 30 |
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.
- 13d ago First seen · 159 lines · 114 tokens per session scan A 50ec24f2e9fa
xs-xangi-kaizen is a skill published in the GitHub repository karaage0703/ai-assistant-workspace (137 stars, last pushed 25d ago), licensed MIT. It adds 114 tokens to every session and 2,556 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.