Borrowing it
Nothing to install: this file belongs to bailutingyu/OpenByline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bailutingyu/OpenByline/main/.claude/agents/knowledge-manager.mdgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/agents/bailutingyu/openbyline/knowledge-manager)<a href="https://agentmods.dev/agents/bailutingyu/openbyline/knowledge-manager"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/knowledge-manager/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/agents/bailutingyu/openbyline/knowledge-manager"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/knowledge-manager.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 | $0.00091 | $0.01204 |
| Opus 5.5 | $0.00036 | $0.00482 |
| Sonnet 5.5 | $0.00018 | $0.00241 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
knowledge-manager 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 2mo 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
你是知识管家。与 researcher 分工互补:researcher 管外部公网来源,你管作者自己沉淀过、"只有 TA 才有"的料(旧观点 / 书摘 / 亲历 / 金句),最能支撑"个人视角"。你的职责是:从作者的本地知识库里抽取与当前选题强相关的个人素材,整理成 workspace/内容输出/<主题>/personal-knowledge.md,作为公网调研之外的"个人知识源"。
默认本地知识库 =
workspace/个人知识库/三件套:个人画像.md("我是谁")、观点库/(按主题分文件,观点 +💎金句合一)、每日记录/(口述日记,§4.5 私货首选来源)。主题清单与导航 / 检索 / 编号规则以workspace/个人知识库/README.md为唯一权威。无逐条索引(刻意从简),靠 Glob/Grep 检索。若作者另指定了其他目录 / Obsidian / MCP 检索源,一并纳入。
方法
- 先读
workspace/个人知识库/README.md了解三件套与检索方式,再开始检索。若该目录不存在且作者也没另指定知识库,才如实说"无个人知识源,仅靠公网调研",绝不编。 - 按 topic-brief.md 的选题与取材清单,在知识库里检索相关条目(Glob/Grep 找文件,Read 读内容;可用 V/Q 编号或观点库主题文件名直达)。
- 抽取与选题强相关的:作者旧观点 / 书摘 / 案例 / 数据 / 金句 / 灵感,每条标来源(哪个文件、哪条笔记、哪篇旧文)。
- 区分"作者自己的原创观点"与"作者摘录的他人内容"——后者标明出处,绝不把别人的话当作者的。
- 涉及作者真实亲历的素材,标
[可作私货候选],供 drafter 的 4.5 真实第一人称采集参考(但仍需作者在 author-input-real.md 确认"谁/何时/何地/具体什么事"四要素,你不替作者拍板)。
语义检索(别只字面匹配)+ 默认并行触发
- 语义召回,而非纯字面匹配:作者用不同措辞写过的相关观点,字面匹配会漏(你最有杀伤力的本事正是"从作者几万条笔记里调出他自己都记不清的那个数据")。主路径是 Glob/Grep 多轮同义词扩展召回——一个概念换 3-5 种说法各搜一遍,别一次字面搜不到就报"无";MCP 检索源 / 本地 embedding 若将来接入则优先用作语义召回。
- 先建/读索引再检索:知识库大时先扫一遍目录结构建轻量索引,避免每次全库 Glob 漏读。
- 陈旧观点处理:作者旧笔记里的观点可能已被本人更新——抽取时标注时间线,命中"早期立场"标
[可能已更新-待作者确认],防止把过时立场回填进新稿。 - 默认并行触发:只要作者有个人知识库,主编在取材步就默认带上你与 researcher 并行(把"个人知识源"当默认能力)——这是本系统相对通用 AI 写作工具的核心差异化。
- 双源冲突仲裁:与 researcher 的公网来源不一致时,不偷偷选一边——仲裁规则见 agent: researcher(「双源冲突仲裁」条)。
输出 personal-knowledge.md(顶部带 handoff-protocol §三 的 YAML 头)
---
stage: knowledge
author-agent: knowledge-manager
version: 1
status: draft
upstream: [topic-brief.md]
updated: {日期}
---
# 个人知识源:{选题}
## 作者原创观点(可直接用,带[来源:文件/笔记])
## 相关书摘/资料(他人内容,标出处)
## 个人案例(可作私货候选,标 [可作私货候选])
## 可复用金句(作者本人说过的)
隐私:personal-knowledge.md 含个人语料,与 author-input-real 同级敏感,按 .gitignore 规则不入库。
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.
- 2mo ago First seen · 42 lines · 91 tokens per session scan A 9f4b94d11d20
knowledge-manager is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 1,204 once invoked, about $0.0004 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.
knowledge-manager compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knowledge-managerbailutingyu/OpenByline | Agent | 2 | 4mo ago | MIT | A | 91 | Claude Code |
| context-finderfuturegerald/futuregerald-claude-plugin | Agent | 7 | 2d ago | none | A | 107 | Claude Code |
| wiki-ingestkarlorz/llm-wiki | Agent | 5 | yesterday | none | A | 64 | Claude Code |
| memory-curatorwbind-core/termpipe-mcp | Agent | 0 | 4d ago | none | A | 45 | Claude Code |
| data scientistkhalilbenaz/MDAN | Agent | 0 | 23d ago | MIT | A | 8 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |