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/decomposenpx skills add iamvonpasion/hashb --skill decomposegit 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/decompose)<a href="https://agentmods.dev/skills/iamvonpasion/hashb/decompose"><img src="https://agentmods.dev/badge/skills/iamvonpasion/hashb/decompose.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 5.1 | $0.00071 | $0.05311 |
| Opus 5 | $0.00036 | $0.02655 |
| Sonnet 5 | $0.00014 | $0.01062 |
| Haiku 4.5 | $0.00007 | $0.00531 |
Grade A, and why
decompose 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 6d 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.
- 6d ago First seen · 547 lines · 71 tokens per session scan A 089f109d5478
decompose is a skill published in the GitHub repository iamvonpasion/hashb (2 stars, last pushed 3mo ago), with no licence file. It adds 71 tokens to every session and 5,311 once invoked, about $0.0004 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
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
cyxj-blog-pub
把文章发布到 Astro 博客。生成符合规范的 post（frontmatter 必填项校验、 kebab-case 文件名、正文图片全部换成图床公网 URL），放进 src/content/posts/，再 build 并部署。产出物在博客仓库，不在内容创作工作区。 触发词：发布到博客、发博客、博客发文、上博客、Astro 发布、blog 发布。.
cyxj-transcript
把视频/录音的逐字稿整理成结构化文章草稿。去口语化、加小标题分段、 数据用表格整理，原始逐字稿保留在文末备查，产出 Obsidian Markdown， 可直接接 cyxj-wechat-pub（公众号）或 cyxj-blog-pub（博客）排版。 触发词：转稿、逐字稿整理、把这个稿子整理成文章、逐字稿转文章、口播稿成文。.
document
Generate minimal documentation through parallel agents.
cyxj-jingxuan
陈与小金的「抖音精选申请文案生成器」。读一条视频的成片字幕/逐字稿，按固定四段式 （原创定性→深度证明→受众价值→平台对齐）写一段 150-250 字、可直接粘贴到抖音精选 官方群的申请文案。站在审核员视角写：替他把通过理由写好，降低他的判断成本。 铁律：每条理由必须能在视频内容里找到对应，禁止空泛套话；数据只用真实后台数据，没有就问，不许编。 触发方式：写精选申请、精选申请、申请精选、帮我写精选申请文案、这条视频申请精选怎么写、/cyxj-jingxuan。.
full-pm-cycle
编排从市场研究到上线后分析的完整产品管理周期。用于综合产品规划、0-1 产品开发，或当用户说"完整产品计划"、"完整 PM 周期"、"从研究到上线"时使用。支持 HTML 原型输出格式。采用 Plan-and-Execute 模式，包含完整的阶段定义、状态追踪和质量门控。 Also triggers on: complete product plan, full PM cycle, from research to launch, 0 to 1 product development.