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/iamvonpasion/hashb/fixnpx skills add iamvonpasion/hashb --skill fixgit clone --depth 1 https://github.com/iamvonpasion/hashbWrote 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/iamvonpasion/hashb/fix)<a href="https://agentmods.dev/skills/iamvonpasion/hashb/fix"><img src="https://agentmods.dev/badge/skills/iamvonpasion/hashb/fix.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 | $0.00019 | $0.04482 |
| Opus 5 | $0.00010 | $0.02241 |
| Sonnet 5 | $0.00004 | $0.00896 |
| Haiku 4.5 | $0.00002 | $0.00448 |
Grade A, and why
fix 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 5d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 5d ago First seen · 477 lines · 19 tokens per session scan A 9752bf183a4e
fix is a skill published in the GitHub repository iamvonpasion/hashb (2 stars, last pushed 3mo ago), with no licence file. It adds 19 tokens to every session and 4,482 once invoked, about $0.0001 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
cyxj-data-review
陈与小金的「抖音平台数据复盘诊断」。读小陈导出的抖音数据，跑一套证据驱动的诊断， 回答一个问题：靠收藏把长视频持续推、再转化涨粉、最终进抖音精选——这条路，数据里跑没跑通。 赛道：非程序员用 Claude Code/Codex 做一切，知识视频冲抖音精选。KPI 链 = 收藏 → 涨粉 → 进精选。 铁律：盘点没和用户确认前，禁止出任何诊断结论。每条结论必标【事实】【推断】【未知】，数据里没有的不许编。 触发方式：/cyxj-data-review、复盘我的数据、诊断我的平台数据、数据复盘、看看我最近数据、我的抖音数据怎么样、这条视频数据怎么样、精选诊断。.
cyxj-content
陈与小金的「知识视频内容诊断」。把一个已定选题，诊断成能冲抖音精选的 3 分钟以上知识视频。 不是短视频带货，是 3 分钟+ 知识口播/演示冲精选。 触发方式：/cyxj-content、内容诊断、这条视频内容怎么做、帮我看看这条稿、视频内容怎么做更好。 不做已发布视频的数据复盘（那是 cyxj-data-review 的活）。 边界：本 skill 专供陈与小金账号（3 分钟+ 知识视频冲抖音精选）；超出该范围的诊断请求按普通对话处理。.
cyxj-hook
陈与小金的「知识视频开头/钩子」优化。诊断 3 分钟以上知识视频（目标抖音精选）的开头问题，并生成优化方案。 不是 15 秒短视频带货，是 3 分钟+ 知识口播冲精选——钩子负责留人，但完播靠整条价值密度；开头不是骗点击，是「承诺一个值得看完的获得感」。 触发方式：/cyxj-hook、优化我的视频开头、知识视频开头怎么写、帮我看开头、开头钩子。 边界：本 skill 专供陈与小金账号（3 分钟+ 知识视频冲抖音精选）；超出该范围的开头优化请求按普通对话处理。.
cyxj-youtube-topics
YouTube 选题发现 + 判断。搜索 "Claude Code" 相关最近 48 小时新视频， 去重、按话题聚类、做硬信号 + 字幕内容分析，输出带 verdict（值得做/观望/跟风/跳过）+ 理由 + 差异化切口建议的选题报告。写入 Obsidian 选题库。 触发方式：「YouTube 选题」「找 YouTube 选题」「YouTube 最近有什么」「帮我找找最近的新选题」「跑一下选题发现」「有什么新视频」 边界：只做 YouTube 新视频的选题发现与判断；泛选题、短视频 IP 人群选题、文案式出选题不归本 skill。.
design
Generate a feature design (design.md) in specs/{feature}/ with user stories, acceptance criteria, technical approach, API contracts, and research decisions.
cyxj-release-kit
陈与小金的视频发布物料一条龙：成片定稿后，一次产出 6 平台「标题+简介」（YouTube/B站/抖音 主平台, 视频号/TikTok/小红书 分发平台）+ 三比例封面（4:3 为工作台首项,另含 16:9 / 3:4,HTML 封面工作台出图, 文字零错字零裁切） 上传用 JPG。封面走「无字底图 + HTML 排字」路线,不再用生图赌中文渲染。 触发方式:/cyxj-release-kit、发布物料、出发布包、取标题、六平台标题、写标题和简介、 做封面(HTML/工作台)、封面工作台、视频要发布了。 凡是"视频做完了准备发"的场景都应该用本 skill——哪怕用户只提了其中一样(只要标题/只要封面), 也按本 skill…