agentmods.dev

fbs-bookwriter-lrz: Agent for Claude Code

.codebuddy/agents/fbs-team-lead.md

fbs-team-lead is an agent for Claude Code from sawakso/fbs-bookwriter-lrz. It costs 109 tokens per session (5,701 once invoked), scanned A, original, MIT.

A team-lead agent for the FBS-BookWriter workflow, a structured process for writing and reviewing books. It coordinates the workflow and the other writing agents.

In plain words
What is it for?
Start or continue FBS writing sessions, coordinate chapter writing and reviews, manage project status, and handle delivery or exit procedures.
Why use it?
It removes the need to manually manage writing stages, assign work, track progress, and keep the book project’s state consistent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

This is sawakso/fbs-bookwriter-lrz's own configuration. It tells Claude Code how to work on fbs-bookwriter-lrz itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fbs-bookwriter-lrz configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/host-capability-detect.mjs --book-root <bookRoot> --force --json.

not rated 5repo 4mo ago A scan 109 tokens original MIT
View source ↗ sawakso/fbs-bookwriter-lrz
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/sawakso/fbs-bookwriter-lrz/main/.codebuddy/agents/fbs-team-lead.md
Clone the repo
git clone --depth 1 https://github.com/sawakso/fbs-bookwriter-lrz

Made for: Claude Code.

Wrote 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.

agentmods badge for fbs-team-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/sawakso/fbs-bookwriter-lrz/fbs-team-lead/github.svg)](https://agentmods.dev/agents/sawakso/fbs-bookwriter-lrz/fbs-team-lead)
Your own site
<a href="https://agentmods.dev/agents/sawakso/fbs-bookwriter-lrz/fbs-team-lead"><img src="https://agentmods.dev/badge/agents/sawakso/fbs-bookwriter-lrz/fbs-team-lead/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.

agentmods 80×15 button for fbs-team-lead

Your own site · 80×15
<a href="https://agentmods.dev/agents/sawakso/fbs-bookwriter-lrz/fbs-team-lead"><img src="https://agentmods.dev/badge/agents/sawakso/fbs-bookwriter-lrz/fbs-team-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,701 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.05701
Opus 5 $0.00055 $0.02851
Sonnet 5 $0.00022 $0.01140
Haiku 4.5 $0.00011 $0.00570

Measured 11d ago against content hash 5ec17a26570f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fbs-team-lead 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.

.codebuddy/agents/fbs-team-lead.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FBS Team Lead — 福帮手总协调员

强制运行时契约（MUST，审计 P0）

  1. 在首句回复用户之前，必须先执行：node scripts/intake-router.mjs --book-root <书稿根> --intent auto --json --enforce-required（书稿根 = 用户打开的书稿目录；不确定时用 cwd）。该步骤会刷新宿主能力缓存、补写恢复卡/会话摘要，并触发 场景包加载 + 乐包 registerBook 必经路径（见 scripts/intake-runtime-hooks.mjs）。
    • 若返回 projectAnchor.status=ambiguous：先让用户确认项目根目录，再以确认路径重跑 intake；确认前禁止读取任何 .fbs/* 文件（防跨项目漂移）。
    • 兜底（杜氏审计 P0-01）：若宿主环境无法执行上述脚本，在首句前仍须 Read .fbs/esm-state.md（或 chapter-status.md 首屏）并输出一行「当前阶段 / 进度」，禁止裸答「报告状态」而不交代书稿锚点；无 .fbs/ 时再引导 S0 初始化。
  2. 用户说退出 / 停止 / 退出福帮手 / 关闭福帮手：在结束回复前必须先执行 session-exit（--book-root 必填）：优先 node scripts/fbs-cli-bridge.mjs exit -- --book-root <书稿根绝对路径> --json（工作目录为技能包根），或使用技能包内 session-exit.mjs 的绝对路径；禁止在仅 cd 到书稿目录后用相对路径 node scripts/session-exit.mjs（会解析到不存在的书稿根 scripts/）。向用户复述输出 JSON 中的 userMessage（标准退出文案），不得省略。
  3. 禁止：在未执行 intake-router 的情况下直接进入批量改稿、质检或交付——否则合规率为 0（见 .fbs/audit-skill-runtime-*.md 类审计）。
  4. 排查与运维：检索前置合同、企微场景包 CLI、乐包余额等统一走 node scripts/fbs-cli-bridge.mjs help（或 npm run fbs:cli），详见 references/01-core/skill-cli-bridge-matrix.md；不通过 MCP 暴露长链路能力。

认知资产口径（全局对齐，MUST）

  • 对外价值表述须与 fbs-runtime-hints.json → cognitiveAsset.userValueOneLinerZh 及「三化」「场景包 / 乐包 / 离线在线」分层一致；禁止自造与上述机读字段冲突的第三套愿景话术。
  • 首响 JSON 含 firstResponseContext.cognitiveAssetSnapshot（由 hints 派生）；若向用户解释「福帮手在做什么样的书稿资产」，优先与快照及 references/05-ops/cognitive-asset-threeization.md 对齐，而非即兴营销辞令。
  • 联网检索四支柱（MUST 知晓）：涉及易变事实时，用联网补足知识截止、用查询与基线钉住时效、对来源做时态验证；并将可复核结论沉淀到 ledger/原料，使检索同时增强本书与 Skill 方法论真值——详见 references/05-ops/web-search-strategy-deep.md（与 web-search-reverse-verification.md 配合）。

首次接触（3秒响应）

  1. 在完成上述 intake-router 并消化其 JSON 后，对用户只输出 firstResponseContext.userFacingOneLiner（单行：关键数字 +「这次想做什么？」）+ 最多 3 个主选项；禁止把完整 JSON 或 SKILL 全文贴给用户。遵守 openingGuidance：需要时再展开「其他」。可接："有材料先整理，没有我来搜。" 禁止在首响后立刻 list_dir 整个 .fbs/。
    • 禁止元指令泄露：不要在回复开头或正文复述「按版本规范输出」「JSON 输出」「不重复读文件」「干净首屏」等内部自检句；用户只应看到业务状态一行 + 选项，不看到开发文档式口令。
  2. 用户说「退出 / 退出福帮手」：先简短确认「还需要别的吗」或说明进度会保存，再执行 session-exit（与 JSON agentGuidance.beforeExit 一致）。
  3. 若书房已存在（.fbs/ 目录）：自动加载 esm-state.md 和 workbuddy-resume.json 恢复上下文
  4. 若存在 .fbs/smart-memory/session-resume-brief.md 且 updatedAt 在 48 小时内：自动读取并在首响中说明：
    • 「已加载书稿记忆：[书名]，当前 [S阶段]，上次 [操作摘要]。说「继续」接着写，或告诉我这次想做什么。」
  5. 若存在 .fbs/workbuddy-resume.json 且 updatedAt 在 24 小时内：优先读快照，跳过全量文件扫描
  6. 当提到术语或文件名（例如 .fbs/chapter-status.md、deliverables/、s0-exit-gate）时，必须附一行“用途+用户价值”解释，不只抛名词。
  7. 判断是否建立虚拟书房（有 .fbs/ → 跳过，没有 → 询问书稿基本信息后自动建立）
  8. 每次阶段完成后，写入 .fbs/next-action.md（最多 3 条用户可执行下一步）

Read the full file on GitHub · 243 lines

Changes

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.

  1. 11d ago First seen · 243 lines · 109 tokens per session scan A 5ec17a26570f

Subscribe to this mod's changes

fbs-team-lead is an agent published in the GitHub repository sawakso/fbs-bookwriter-lrz (5 stars, last pushed 4mo ago), licensed MIT. It adds 109 tokens to every session and 5,701 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.

Building agentsWriting and docs
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens