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 cloud99277/KitClaw --skill conversation-distillergit clone --depth 1 https://github.com/cloud99277/KitClawWrote 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/cloud99277/kitclaw/conversation-distiller)<a href="https://agentmods.dev/skills/cloud99277/kitclaw/conversation-distiller"><img src="https://agentmods.dev/badge/skills/cloud99277/kitclaw/conversation-distiller/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/cloud99277/kitclaw/conversation-distiller"><img src="https://agentmods.dev/badge/skills/cloud99277/kitclaw/conversation-distiller.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.00829 |
| Opus 5.5 | $0.00023 | $0.00332 |
| Sonnet 5.5 | $0.00011 | $0.00166 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
conversation-distiller 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 1mo 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.
What it actually says
Conversation Distiller
将当前对话提炼为一份结构化 Markdown 笔记，并把它写入 L3 知识库。
它的职责不是保存完整聊天记录，而是把可复用的结论、排查过程和最终方案沉淀为长期知识。
什么时候用
- 用户说“保存这段对话”“提炼一下并保存”“把刚才的问答整理成笔记”
- 当前问题已经解决，值得作为 L3 文档长期保留
- 你希望这次对话能被后续的
knowledge-search检索到
快速开始
推荐始终使用 JSON mode，避免 shell 转义问题：
cat >/tmp/distill.json <<'JSON'
{
"title": "[Dev] 端口冲突排查",
"content": "## 背景与起因\n...\n\n## 排查过程\n1. ...\n\n## 最终方案\n...",
"base_dir": "~/knowledge-base/40_Agent_Notes/distilled-conversations"
}
JSON
python3 ~/.ai-skills/conversation-distiller/scripts/save_note.py \
--json /tmp/distill.json \
--print-json
如果不提供 base_dir，默认行为是：
- 读取
~/.ai-memory/config.json - 取其中第一个
l3_paths作为知识根目录 - 写入
<knowledge-root>/40_Agent_Notes/distilled-conversations/
建议的提炼结构
## 背景与起因
[具体问题、错误、环境]
## 排查/探索过程
1. [步骤]
2. [步骤]
## 关键转折
[哪一步揭示了问题本质]
## 最终方案
[最终做法 + 原理]
## 延伸知识点
- [可选]
自动入库行为
当输出目录位于已配置的 L3 路径下时，脚本会自动：
- 运行
ensure-knowledge-frontmatter.py - 运行
rag-engine/knowledge_index.py --update
这样新保存的笔记会尽快进入 L3 检索链路。
环境变量
可选环境变量：
CONVERSATION_DISTILLER_BASE_DIR：覆盖默认输出目录CONVERSATION_DISTILLER_KNOWLEDGE_ROOT：覆盖自动识别的知识根目录CONVERSATION_DISTILLER_DB_PATH：覆盖 LanceDB 索引路径CONVERSATION_DISTILLER_AUTO_INGEST：设为false可关闭自动入库CONVERSATION_DISTILLER_INDEXER_PYTHON：覆盖 indexer 的 Python 解释器
设计约束
- 脚本本身零外部依赖（stdlib only）
- 默认只处理“当前对话”的提炼，不负责历史对话检索
- 自动入库依赖
KitClaw自带的memory-manager和rag-engine - 对话正文建议通过 JSON 文件传递，不建议用 positional args
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.
- 1mo ago First seen · 101 lines · 57 tokens per session scan A 060201a84170
conversation-distiller is a skill published in the GitHub repository cloud99277/KitClaw (5 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 829 once invoked, about $0.0002 per session on Opus 5.5. 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
llm-wiki
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture, schema, or organization decisions; operational ingest/query/lint work uses dedicated skills.
wiki-lint
Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues. Use for maintenance or health checks. Default is report-only; use wiki-dedup for page-identity merges.
wiki-status
Report wiki ingestion/completeness state, pending source delta, structural insights, or maintenance equilibrium. Use for remaining-work/status questions, hubs and bridges, or whether maintenance skills still have pending changes. wiki-digest summarizes learned knowledge instead.
wiki-import
Import a wiki graph into the current vault from graph.json or an OKF/markdown bundle. Use for transferring previously exported wiki content between vaults; pair with wiki-export for the reverse direction.
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
hermes-history-ingest
Ingest Hermes agent history into Obsidian as distilled knowledge. Use for importing or mining /.hermes sessions, memories, or logs; use wiki-agent for targeted topic-only cross-agent recall.