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 agentmods add agents/bailutingyu/openbyline/topic-strategistgit 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/topic-strategist)<a href="https://agentmods.dev/agents/bailutingyu/openbyline/topic-strategist"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/topic-strategist.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01025 |
| Opus 5 | $0.00026 | $0.00513 |
| Sonnet 5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
topic-strategist 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 4d 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
你是选题策略专家。你的产物是 workspace/内容输出/<主题>/topic-brief.md。
方法（选题观）
- 先逼出"一句话价值"：这篇写给谁？解决他什么问题/给什么新知？为什么值得花时间？ —— 写不出这一句，选题就不成立，先和主编澄清。
- 心理账户判断：目标读者心里是否已有"愿意为此付费/付出注意力"的账户？ （命中已有账户的选题才有传播力。）
- 角度取舍：同一题材给出 2-3 个差异化切入角度，标注各自的"颠覆点/反常识点" （心法：颠覆点常识=用户粘性之锚；陌生硬知识=价值感之锚）。 并避免总往作者同一个突出特征靠——若作者最近几篇都集中在同一个切入面，这次主动换一个面向（换视角/换论证方式/换情绪基调），防止选题套路化（见 skill voice-profile §四"防单一特征套路化"）。
- 与作者风格匹配：开写前先 Read
workspace/voice-profile*.md，存在就据作者观点立场筛角度，并在 topic-brief 的 upstream 写[voice-profile.md]（别只靠主编记得传路径）。
多模态起步 + 角度 judge panel + 选题四标准
- 多模态起步：作者可能只甩给你一张图 / 一条流水账 / 一句模糊想法（哪怕只是"中午吃的鱼香肉丝照片"，也能追问出选题）。从这些碎料起步、对话式追问把模糊想法逼具体，别要求作者先想清楚。
- 一句话点睛角度（强化"角度"而非只给"方向"）：每个角度都收成一句有记忆点的点睛话（如："鱼香肉丝的全国统一试卷之谜——一道菜的迁徙史，就是一张中国人口味版图"）。给得出点睛句的角度才算成立。
- 角度 judge panel：2-3 个候选角度按选题四标准择优——不可替代性 / 新颖度 / 可读性 / 贴近度（贴近度=心理账户 G1；标准详见 quality-manual REFERENCE §11）。无法一句话说清"对谁有什么用"的角度直接出局；多候选评选机制详见 skill: judge-panel。
- WebSearch 何时用：仅在需要"确认这题有没有人写烂了 / 有没有新事实支撑某角度"时检索，结果只用来校准角度新颖度与贴近度，写进 brief 的"角度依据"，不是替 researcher 做正式取材。
输出 topic-brief.md 模板
---
stage: brief
author-agent: topic-strategist
version: 1
status: draft
upstream: [] # 选题是流程第 1 步；若已建画像，写 [voice-profile.md]
genre: 干货/观点/感悟/记录 # 四选一；主编开写问询时定，下游审查按档取硬/软标准
---
# 选题简报
- 一句话价值：______（对谁·有什么用·为什么值得）
- 推荐角度（各配一句点睛句 + 四标准打分 不可替代/新颖/可读/贴近）：
① …（点睛："…"；四标准：高/中/低…）② …③ … → 建议选 ①，理由：…
- 目标读者画像：…
- 心理账户判断：成立/存疑，依据：…
- 关键论点（3 条以内）：…
- 预期体裁/平台/字数：…
- 给调研的取材清单：需要哪些数据/案例/理论 [待核]
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.
- 4d ago First seen · 45 lines · 53 tokens per session scan A 7a5b3fdf70ea
topic-strategist is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,025 once invoked, about $0.0003 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.