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 hanmirage/deepdepcat --skill depwork-contentgit clone --depth 1 https://github.com/hanmirage/deepdepcatWrote 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/hanmirage/deepdepcat/depwork-content)<a href="https://agentmods.dev/skills/hanmirage/deepdepcat/depwork-content"><img src="https://agentmods.dev/badge/skills/hanmirage/deepdepcat/depwork-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/hanmirage/deepdepcat/depwork-content"><img src="https://agentmods.dev/badge/skills/hanmirage/deepdepcat/depwork-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 | $0.00079 | $0.00520 |
| Opus 5.5 | $0.00032 | $0.00208 |
| Sonnet 5.5 | $0.00016 | $0.00104 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
depwork-content 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 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.
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
自媒体内容创作模板
开头定生死（前 3 行）
- 钩子：具体冲突/反常识/数字，不用「在当今社会」；
- 承诺：读者 30 秒内知道「读完能得到什么」；
- 示例：「我花 3 天跑了 20 个资料源，发现 90% 的选题都死在第一步。」
结构（推荐任一）
- 清单式：3 个要点 + 每个配一个例子（适合小红书/知乎）；
- 问题解决式：痛点 → 原因 → 方法 → 验证（适合公众号）；
- 故事式：冲突 → 转折 → 结论（适合视频脚本）；
- 对比式：A vs B，逐维度（适合测评/调研类）。
平台差异
- 公众号：完整论证 + 段落短 + 小标题；
- 小红书：标题 ≤ 20 字、emoji 适量、段落 ≤ 3 行、结尾行动号召；
- 抖音脚本：前 3 秒钩子 + 每 15 秒一个信息点；
- 知乎：前置结论，引用与数据充足。
收尾
- 一句总结（可被截图引用）；
- 一个行动建议；
- 互动问题（只问一个）。
导出
- 短内容 → 纯文本/Markdown；
- 长文/图文 →
docx_generate； - 需排版样张 →
pdf_generate。
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 · 42 lines · 79 tokens per session scan A bdfab6f558af
depwork-content is a skill published in the GitHub repository hanmirage/deepdepcat (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 520 once invoked, about $0.0003 per session on Opus 5.5. 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.
depwork-content compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| depwork-contenthanmirage/deepdepcat | Skill | 10 | 2mo ago | Apache-2.0 | A | 79 | Claude Code |
| eac-desktop-tipszouyuxuan122/DSH-Desktop-EAC | Skill | 2.1k | 20d ago | MIT | A | 80 | Claude Code, Codex |
| gog-workspaceAtomicBot-ai/Atomic-Chat | Skill | 1.9k | yesterday | none | A | 68 | Claude Code, Codex |
| apple-calendarAtomicBot-ai/Atomic-Chat | Skill | 1.9k | yesterday | none | A | 45 | Claude Code, Codex |
| apple-remindersAtomicBot-ai/Atomic-Chat | Skill | 1.9k | yesterday | none | A | 31 | Claude Code, Codex |
| githubAtomicBot-ai/Atomic-Chat | Skill | 1.9k | yesterday | none | A | 48 | Claude Code, Codex |
| dockerAtomicBot-ai/Atomic-Chat | Skill | 1.9k | yesterday | none | A | 44 | Claude Code, Codex |