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 petar-djukic/writing-skills --skill patent-disclosuregit clone --depth 1 https://github.com/petar-djukic/writing-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/petar-djukic/writing-skills/patent-disclosure)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/patent-disclosure"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/patent-disclosure/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/petar-djukic/writing-skills/patent-disclosure"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/patent-disclosure.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 | $0.00130 | $0.01240 |
| Opus 5 | $0.00065 | $0.00620 |
| Sonnet 5 | $0.00026 | $0.00248 |
| Haiku 4.5 | $0.00013 | $0.00124 |
Grade A, and why
patent-disclosure 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patent disclosure
This skill turns an invention into a disclosure that survives a patent professional's four-axis evaluation. It is domain-independent: everything domain-specific comes from a project context file, never from the skill.
Where things live
- Framework:
references/four-axis-framework.md— the four evaluation axes with targets, plus detectability. - Writing guide:
references/section-guide.md— the eleven sections, the problem-statement formula, the writing order, style rules. - Patterns:
references/patterns-and-antipatterns.md— claim anatomy, four strong patterns, five anti-patterns with fixes. - Register:
references/technical-register.md— anthropomorphic and casual vocabulary with technical replacements, the term-of-art exception, the companion-disclosure independence rule. - Skeleton:
assets/disclosure-template.md— the section scaffold to copy for a new disclosure. - Gate:
assets/checklist.md— the patentability checklist and the self-assessment rubric with target scores.
Domain context (required input)
Look for patent-context.md in the working directory (or a file the user
names). It supplies what the skill deliberately does not contain:
- the technology domain and its terminology
- pointers to the project's architecture documents
- known competitors and prior-art starting points (assignees to search)
- relevant standards bodies and any standardization plans
- scenario, roadmap, and commercial material for Sections 5.3 and 9
If the file is absent, ask the user for the domain and any known prior art in one question, then proceed with generic search strategies. Never invent commercial figures, expert names, or competitor claims — every Section 9 fact traces to the context file or the user.
The workflow
1. Claim first
Draft (or receive) the claim and treat it as the north star: enumerate its limitations, confirm each is an intentional technical element, and verify material exists to support every one. Offer the three-scope ladder (broad / medium / narrow) from the framework reference.
What ships with it
6 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.
- 12d ago First seen · 121 lines · 130 tokens per session scan A e74baa46c088
patent-disclosure is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It adds 130 tokens to every session and 1,240 once invoked, about $0.0006 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
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
structural-humanizer
Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…
legal-humanizer
Write or rewrite legal and professional drafting so it reads as careful drafting, not chatbot output, while preserving precision, defined terms, and formal structure. Use for contracts, clauses, legal memos, briefs, policies, terms of service, and demand letters, whether editing existing text or when the user asks…
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story
A Chinese-language routing tool for fiction writers that directs requests to tools for outlining, writing, analysis, reviews, covers, importing novels, browser control, and project management.
fedramp
Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…