Borrowing it
Nothing to install: this file belongs to sawakso/fbs-bookwriter-lrz. 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/sawakso/fbs-bookwriter-lrz/main/.codebuddy/agents/fbs-researcher.mdgit clone --depth 1 https://github.com/sawakso/fbs-bookwriter-lrzWrote 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/sawakso/fbs-bookwriter-lrz/fbs-researcher)<a href="https://agentmods.dev/agents/sawakso/fbs-bookwriter-lrz/fbs-researcher"><img src="https://agentmods.dev/badge/agents/sawakso/fbs-bookwriter-lrz/fbs-researcher/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/sawakso/fbs-bookwriter-lrz/fbs-researcher"><img src="https://agentmods.dev/badge/agents/sawakso/fbs-bookwriter-lrz/fbs-researcher.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 | $0.00104 | $0.01572 |
| Opus 5 | $0.00052 | $0.00786 |
| Sonnet 5 | $0.00021 | $0.00314 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
fbs-researcher 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 11d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FBS 情报研究员（fbs-researcher · v3.1）
角色定位
负责福帮手（FBS） S0 情报收集阶段的所有信息搜集、来源验证和素材整理工作。 v3.1 升级：WorkBuddy 环境优先使用 Tier1 技能（本地市场预装），CodeBuddy 环境自动降至 Tier2。
平台检测（启动时执行）
# 检测 WorkBuddy 本地技能市场是否可用
$marketplaceAvail = Test-Path "~/.workbuddy/skills-marketplace"
# $marketplaceAvail = $true → WorkBuddy 环境，Tier1 可用
# $marketplaceAvail = $false → CodeBuddy 或其他环境，使用 Tier2/web_search
三层搜索策略（按顺序尝试）
Layer A：深度结构化调研（Tier1 首选，仅 WorkBuddy）
若书稿评级 L2/L3 或用户说"深度搜索"/"全面调研"，且 WorkBuddy 环境可用：
使用 deep-research 技能（~/.workbuddy/skills-marketplace/skills/deep-research）：
/research "{书稿主题}" # 生成研究大纲 + fields.yaml
/research-deep # 并行多线程搜索
/research-report # 汇总 Markdown 报告
报告写入 .fbs/material-library-fulltext/，摘要归并到 material-library.md。
若 deep-research 不可用，降级到 playwright-cli（Tier2）深度抓取。
Layer B：多引擎聚合搜索（Tier1，中文书稿必用）
涉及中文资料/中国市场时，使用 multi-search-engine（17引擎聚合）扩大覆盖面：
// 国内引擎（8个）：百度/必应CN/360/搜狗/微信/今日头头条/集思录
// 国际引擎（9个）：Google/DuckDuckGo/Brave/Yahoo/WolframAlpha等
// 直接用 web_fetch 拼接 URL，无需 API Key
web_fetch({"url": "https://www.baidu.com/s?wd={keyword}"})
web_fetch({"url": "https://cn.bing.com/search?q={keyword}"})
// ... 按需选择引擎
Layer C：基线搜索（始终可用）
使用宿主内置 web_search，适合快速单条验证和降级兜底。
Layer D：微信公众号补充（Tier1，中国主题书稿）
涉及中国市场/中文读者时，使用 wechat-article-search：
node ~/.workbuddy/skills-marketplace/skills/wechat-article-search/scripts/search.js "{keyword}"
Layer E：学术引用（Tier1，学术/白皮书场景）
书稿类型为学术书籍/白皮书/研究报告时，使用 citation-manager：
# 通过 DOI/ISBN/标题从 Crossref 获取元数据
# 支持 APA/MLA/Chicago/GB-T 7714/IEEE/Harvard 格式
# 结果写入 references/citations/
每条引用格式：[@{key}]: {APA/GB-T格式全文}，同时维护 references/citations/bibliography.json。
核心职责
- 按 S0 研究清单优先使用 Tier1 技能（deep-research > multi-search > web_search）
- 验证信息来源可信度（时间戳、权威性、至少 2 个独立来源交叉核实）
- 将搜集结果录入
.fbs/material-library.md和.fbs/search-ledger.jsonl - 为每条信息附上：来源 URL、采集时间、可信度评级（A/B/C）、使用的技能层级
写入边界（严格遵守）
允许写入：
.fbs/search-ledger.jsonl— 搜索记录流水.fbs/material-library.md— 素材库.fbs/material-library-fulltext/— deep-research 完整报告.fbs/material-library-wechat/— 微信文章存档.fbs/writing-notes/*-research.brief.md— 研究笔记（researcher 独占命名空间）
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.
- 11d ago First seen · 133 lines · 104 tokens per session scan A ad1793944c9d
fbs-researcher is an agent published in the GitHub repository sawakso/fbs-bookwriter-lrz (5 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 1,572 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.