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 skills/bailutingyu/openbyline/topic-radarnpx skills add bailutingyu/OpenByline --skill topic-radargit 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/skills/bailutingyu/openbyline/topic-radar)<a href="https://agentmods.dev/skills/bailutingyu/openbyline/topic-radar"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/topic-radar.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 | $0.00105 | $0.02006 |
| Opus 5 | $0.00053 | $0.01003 |
| Sonnet 5 | $0.00021 | $0.00401 |
| Haiku 4.5 | $0.00011 | $0.00201 |
Grade A, and why
topic-radar 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
选题雷达（topic-radar）
把你关注的自媒体内容库（你的本地内容库/，session 没接入先让用户 /add-dir；数据源/库规范详见库根 CLAUDE.md 与 你的本地库说明）盘成一份"对齐作者画像、分级、带私货回填提示"的选题雷达，产出落 workspace/选题雷达/<date>-公众号.md。
信条：雷达只给分级 + 判断 + 私货缺口，不替作者拍板写哪条；成稿另走写作流水线。本系统瓶颈是判断准不准、漏没漏选题，不是吞吐——并行只为精读更快、清点更全。
一、模型分工
轻活用轻模型批量跑、重判断（聚类分级）主编亲做（当前示例：精读 Sonnet / 聚类 Opus，可随版本换）。
| 阶段 | 干什么 | 跑在哪 | 模型 |
|---|---|---|---|
| 精读（可并行 N 片） | 逐篇忠实精读全文 → 出结构化卡片（一句话核心 / 关键数据标口径 / 观点 / 可借鉴写法 / AI·非AI / 与画像潜在相关度初判 / 红线提示）。只忠实提炼、标口径，不下最终分级 | 多个 general-purpose subagent（一条消息多发并行）或 Workflow parallel/pipeline |
Sonnet ✅ |
| 聚类·去重·对齐画像·分级·人称体例·私货回填·事实红线 | 把卡片聚成簇、对齐 voice-profile 定 ★◎○△✕、翻正人称、标待核、列私货缺口 | 主编（主程序/zhubian-orchestrator）亲自做，不外包 | Opus / 会话模型 |
| （可选）judge-panel / 对抗式完整性审查 | 大批量稿(>50篇)时挑漏选/高估/把待核当实据 | 单独 agent | Sonnet 精读侧、Opus 判断侧 |
两条执行路径的写法：
- Agent 工具临时并行（默认）：每个精读 Agent 调用显式带
model: "sonnet"、subagent_type: "general-purpose"；主编自己（会话 Opus）收卡聚类。 - Workflow 工具（开 ultracode、长库大批量时）：精读
agent(prompt, {agentType:'general-purpose', model:'sonnet', schema})；聚类/judge stage 用 Opus 或 return 给主编做。
二、标准跑法（SOP）
- 确认数据最新：
你的本地内容库下git fetch && git status，落后则pull，报一句"拉到 N 篇/已最新"。 - 拉当天清单（按文件名日期 glob，排除两类噪音）：
find 公众号 -name '<YYYY-MM-DD>_*.md' ! -path '*<某恒排除的促销号>*' -size +1c（把你库里那种纯促销、对选题无用的号恒排除；-size +1c滤掉 0B 空文件）。 - 单独捞空占位、防漏：外部同步软件常先建 0B 空文件占位、内容稍后才填。务必另跑一次不带
-size过滤的 find，把 0B 文件单列为"⏳ 待补"，其中和作者强相关的（AI 工具/MCP/独立开发/出图/教育 AI）标"到了优先看"，内容到了做增量补进表、升 v2。 - 完整无截断清点：
find ... | LC_ALL=C sort+ 分账号uniq -c统计全量真实篇数（别信旧产物 source 里的计数）；选题雷达最怕漏选题，清单务必看全。 - 对齐体例 + 画像红线：读
workspace/选题雷达/最近一版产物对齐体例（YAML 头 / 分级图例 / 卡片结构 / 人称）；读workspace/voice-profile.md的【绝对不要】清单与分级红线。 - 分片并行精读（Sonnet）：按主题/账号把当天有效篇数分成 N 片（每片 5–7 篇），并行派精读 agent（见 §一）；prompt 里喂作者画像速览 + 输出 schema + "标口径·不下最终分级·未发布模型警觉"纪律。
- 主编聚类分级产出（Opus）：carry over 全部卡片，亲自聚类去重 → 对齐画像定 ★◎○△✕ → 翻正人称 → 标事实红线 → 列私货回填点 → 写产物。同母题的多条选题要标"择一深做/可缝合"，别让作者自我重复。
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 · 59 lines · 105 tokens per session scan A e211558097af
topic-radar is a skill published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 2,006 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…