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 skills add shadowcz007/skills --skill fill-contentgit clone --depth 1 https://github.com/shadowcz007/skillsWrote 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/shadowcz007/skills/fill-content)<a href="https://agentmods.dev/skills/shadowcz007/skills/fill-content"><img src="https://agentmods.dev/badge/skills/shadowcz007/skills/fill-content/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/skills/shadowcz007/skills/fill-content"><img src="https://agentmods.dev/badge/skills/shadowcz007/skills/fill-content.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 | $0.00115 | $0.00943 |
| Opus 5.5 | $0.00046 | $0.00377 |
| Sonnet 5.5 | $0.00023 | $0.00189 |
| Haiku 4.5 | $0.00012 | $0.00094 |
Grade A, and why
fill-content scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 自动抓取每个 URL 的内容（先 curl，失败时用 Playwright 无头浏览器兜底） What it actually says
何时使用
用户说要补全正文、拉取/抓取无正文条目的正文并更新到 mixdao、或提到 fill content / 无正文 / hasContent 时使用本 skill。
补全正文（Fill Content）
根据 URL 抓取正文，上传前用 AI 梳理为约 250 字案例描述并替代正文回写到 mixdao，仅处理当前尚无正文的条目。
脚本
| 脚本 | 作用 |
|---|---|
scripts/01-fetch-no-content.js |
拉取 mixdao GET /api/latest，过滤出 hasContent === false 的条目，写入 temp/fill-content-{date}.json。 |
scripts/02-fetch-content.js |
读取 01 输出的 JSON，抓取每个 URL 的正文，保存到 temp/{cachedStoryId}.txt。 |
scripts/03-update-from-temp.js |
从 temp 读取正文，上传前用 AI 梳理为约 250 字案例描述并以此替代正文 PATCH 更新。list 必须传 JSON 路径，输出元数据与正文摘要供 Agent 判断；更新必须传至少一个 id，可一次传多条。 |
流程
步骤 1：获取无正文条目
node scripts/01-fetch-no-content.js
输出：temp/fill-content-{date}.json（示例：temp/fill-content-2026-02-17.json）
步骤 2：批量抓取正文
node scripts/02-fetch-content.js temp/fill-content-2026-02-17.json
- 自动抓取每个 URL 的内容（先 curl，失败时用 Playwright 无头浏览器兜底）
- 保存到
temp/{cachedStoryId}.txt - 过滤无效内容（404、登录页等）
- 可中途停止，下次运行会跳过已存在的文件
步骤 3：预览待更新内容（含元数据，供 Agent 做语义判断）
# 推荐：传入步骤 1 的 JSON 路径，输出每条 title、translatedTitle、text 与正文摘要
node scripts/03-update-from-temp.js list temp/fill-content-2026-02-17.json
- 必须传 JSON ：每条输出
cachedStoryId、title、translatedTitle、text（截断）、contentLength、contentPreview（正文前 300 字）。是否与文章主题一致由 Agent 根据上述信息自行判断；其中需排除内容仅为导航/框架、未包含实际正文的条目。存疑条目可在步骤 4 选择不更新。
步骤 4：更新到 mixdao
Agent 做好主题判断后，只更新判定为一致的条目，一次传入多个 cachedStoryId。脚本会先用 AI 将每条正文梳理为约 250 字（简体中文、突出人物/公司等），提交到 mixdao 的是该梳理结果，而非原始长正文。运行前需设置 ANTHROPIC_API_KEY（与 daily-briefing 一致）。
# 更新指定的一条或多条（推荐：判断后只传通过的 id）
node scripts/03-update-from-temp.js <id1> <id2> <id3>
示例：node scripts/03-update-from-temp.js cmlpr8xsb005al70adaskpzl4 cmlpr8xd7002jl70ax1ytgrrt
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 62 lines · 115 tokens per session scan A 241b2d79ae3d
fill-content is a skill published in the GitHub repository shadowcz007/skills (0 stars, last pushed 7mo ago), licensed MIT. It adds 115 tokens to every session and 943 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
fill-content compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fill-contentshadowcz007/skills | Skill | 0 | 7mo ago | MIT | A | 115 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |