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-spontaneous-talkgit 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-spontaneous-talk)<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-spontaneous-talk"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-spontaneous-talk/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-spontaneous-talk"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-spontaneous-talk.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 | $0.00090 | $0.01932 |
| Opus 5 | $0.00045 | $0.00966 |
| Sonnet 5 | $0.00018 | $0.00386 |
| Haiku 4.5 | $0.00009 | $0.00193 |
Grade A, and why
xs-spontaneous-talk 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自発的おしゃべりスキル
AIアシスタントがユーザーに自発的に話しかける。
絶対遵守事項
- 1回の発話は1〜3文程度。長文禁止
- 質問形式で終わると会話が続きやすい
- 自然体で、ロボット感を出さない
- 「スキルに従って話しかけています」等のメタ発言禁止
- ユーザーのプライベート情報を不用意に晒さない
- 内部状態をユーザーに見せない — 確率判定の数値、Step名、状態ファイルの中身、「発話する/しない」の判定過程などは一切表示しない。発話しない場合は何も表示しない。発話する場合は発話内容のみ出力する
- 万が一、内部状態を含むメッセージを送ってしまったら →
xangi tool discord_edit --channel <チャンネルID> --message-id <メッセージID> --content "発話内容のみ"で即編集する
設定
設定は check_speak.sh 内の変数で管理。環境に合わせて編集してください。
SPEAK_PROBABILITY: 20 # 発話確率（%）。cron 30分おきなら平均2.5時間に1回
QUIET_START: 23:00 # 静かにする開始時刻（"none"で無効）
QUIET_END: 08:00 # 静かにする終了時刻（"none"で無効）
MIN_INTERVAL_MINUTES: 60 # 前回発話からの最低間隔（分）
手順
Step 0: 時刻確認（必須！）
最初に必ず date で現在時刻を確認する。 前の流れや思い込みで判断しないこと。
date '+%Y-%m-%d %H:%M %Z'
- quiet hours（デフォルト: 23:00-08:00）の場合 → 即座に終了。何も出力しない。
- quiet hours外 → Step 1 に進む
時刻確認をサボると、深夜帯なのに話しかけてしまう事故が起きる。必ず
dateコマンドで確認すること。
Step 1: 確率判定（スクリプトで自動判定）
スクリプトを実行して判定する。判定結果以外は一切出力しないこと。
bash [SKILL_DIR]/check_speak.sh [WORKSPACE]/memory/spontaneous-talk-state.json
NO_SPEAKが返ったら → 即座に終了。何も出力しない。ツール呼び出しもしない。SPEAKが返ったら → Step 2 に進む
Step 2: 情報収集
発話すると決まったら、以下を並行で収集：
- 現在の日時・曜日 —
date '+%Y-%m-%d %A %H:%M'で確認（曜日を間違えないこと！） - チャンネル履歴 — 現在のチャンネルの最新メッセージを確認
- 今日の日記 —
[WORKSPACE]/memory/YYYYMMDD.mdを読む - メモリ — AGENTS.mdやMEMORY.mdからユーザーの好みや最近の出来事を把握
Step 3: 話題選択
以下のカテゴリからその時に自然な話題を1つ選ぶ：
| カテゴリ | 内容 | 例 |
|---|---|---|
| 会話の続き | チャンネル履歴の流れを拾って続ける | 「そういえばさっきの〇〇、気になって調べたんだけど…」 |
| 気づき・発見 | 日記やワークスペースから面白いネタ | 「今日のcommit見てたんだけど、あの機能いい感じだね」 |
| 雑学・小ネタ | ユーザーの興味に関連した豆知識 | 「知ってた？Pythonの〇〇って実は…」 |
| 気遣い | 時間帯・状況に応じた声かけ | 「お疲れ様〜今日も色々やってたね」 |
| 共有の話題 | ユーザーとの共通の話題 | 「最近あの話の続きどうなった？」 |
選択基準：
- チャンネルに最近の会話があれば → 会話の続き を優先
- 日記に面白い出来事があれば → 気づき を優先
- 特に何もなければ → 気遣い or 共有の話題
Step 4: 発話
現在のチャンネルにそのまま発言する。
トーンガイド:
- AGENTS.mdで定義された性格に従う
- 短くてテンポのいい文
- 質問で終わると会話が続きやすい
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 · 156 lines · 90 tokens per session scan A 2da20047ec25
xs-spontaneous-talk is a skill published in the GitHub repository karaage0703/ai-assistant-workspace (137 stars, last pushed 25d ago), licensed MIT. It adds 90 tokens to every session and 1,932 once invoked, about $0.0005 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.