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.
git clone --depth 1 https://github.com/jiutuhky/my-super-capsuleWrote 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/commands/jiutuhky/my-super-capsule/write-patent)<a href="https://agentmods.dev/commands/jiutuhky/my-super-capsule/write-patent"><img src="https://agentmods.dev/badge/commands/jiutuhky/my-super-capsule/write-patent/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/commands/jiutuhky/my-super-capsule/write-patent"><img src="https://agentmods.dev/badge/commands/jiutuhky/my-super-capsule/write-patent.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 | $0.00048 | $0.00269 |
| Opus 5.5 | $0.00019 | $0.00108 |
| Sonnet 5.5 | $0.00010 | $0.00054 |
| Haiku 4.5 | $0.00005 | $0.00027 |
Grade A, and why
write-patent 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 1mo 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
Step 1: 生成专利文本
Invoke the patent-writer:writing-patent skill and follow it exactly as presented to you.
Wait for Step 1 to fully complete (04_content/description.md 已生成) before proceeding.
Step 2: 生成专利附图 PNG
Invoke the patent-writer:patent-diagram-drawing skill and follow it exactly as presented to you.
The skill will guide you to read description.md and structure_mapping.json from the same project working directory, then generate PNG diagrams into 05_diagrams/.
Wait for Step 2 to fully complete (05_diagrams/ 已生成附图) before proceeding.
Step 3: 合并生成 Word 专利文件
Use the patent-writer:docx-merger agent to merge all content and diagrams into the final Word patent application file.
The agent will read abstract.md, claims.md, description.md and diagrams from 05_diagrams/, then generate 06_final/patent_application.docx.
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.
- 1mo ago First seen · 25 lines · 48 tokens per session scan A 0747721829d4
write-patent is a command published in the GitHub repository jiutuhky/my-super-capsule (12 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 269 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
sign
Sign a PDF — stamp a signature block (name + date, or a PNG signature) on a signed copy.
/accreditation-track
Seguimiento de acreditaciones sanitarias (JCI, EFQM, ISO 9001, ISO 15189). Mapea requisitos a evidencias, detecta gaps, genera reportes de cumplimiento. Prepara auditorías y evaluaciones de terceros.
pipeline-minutar-pdf
Pipeline completo de sentença judicial a partir de PDF (conversão, linha-tempo, relatório, análise, fundamentação, merge).
noirdoc-redact
Redact a local file via noirdoc, placing the clean copy in .noirdoc/cache/.
legal-risk
Analyze sourced covenant clauses and merger-agreement MAC/MAE language with page-level quotes and risk classification.
lawsuit-analysis
A command that analyses legal case documents and produces a structured, self-contained HTML report. It can organise people, claims, responses, evidence, and events from documents such as complaints or briefs.