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 zgbrenner/agentcounsel --skill invention-intakegit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/zgbrenner/agentcounsel/invention-intake)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/invention-intake"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/invention-intake/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/zgbrenner/agentcounsel/invention-intake"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/invention-intake.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 | $0.00039 | $0.03082 |
| Opus 5 | $0.00019 | $0.01541 |
| Sonnet 5 | $0.00008 | $0.00616 |
| Haiku 4.5 | $0.00004 | $0.00308 |
Grade A, and why
Invention Disclosure Intake 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 9d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invention Disclosure Intake
Purpose
Produce a structured first-pass invention disclosure screen that helps patent counsel quickly orient to a proposed invention, identify obvious patentability signals, and flag any urgent filing-deadline concerns. This is draft legal work product for attorney review. It is NOT a patentability opinion, NOT a prior-art search, and does NOT constitute a legal finding that any invention is patentable or patent-eligible.
Use When
- A user presents a new invention and asks whether it is worth pursuing a patent.
- An engineer, product team, or inventor needs a structured disclosure captured before meeting with patent counsel.
- A user wants to understand whether public-disclosure timing creates an urgent filing concern.
- A user needs a first-pass triage to decide whether to commission a formal patentability search and opinion.
- A user wants a structured intake document to brief patent counsel efficiently.
Required Inputs
The following information is needed to run the screen. Provide either a full written disclosure document that covers these points, or answers to each intake question individually.
- Technical essence: what the invention does and how it works, in plain language.
- Problem solved: the technical or practical problem the invention addresses, and why existing approaches fall short.
- Points of distinction: how the invention differs from known prior approaches — in the inventor's own words, without legal characterization.
- Inventors and conception date: names of all individuals who contributed to the inventive concept, and the date (or approximate date) the invention was first conceived.
[CONFIRM: conception date with each named inventor] - Public-disclosure history: any public disclosures already made — including conference presentations, papers, preprints, product launches, trade-show demonstrations, press releases, social media posts, open-source commits, or any disclosure not protected by a non-disclosure agreement — with dates and venues. If all disclosures were made under NDA, confirm the NDA was in place before disclosure.
[CONFIRM: whether any disclosure was made without NDA coverage] - Usage and commercialization status: whether the invention is already in a shipped product, a limited pilot, on the product roadmap, or described only internally or in a publication.
- Technical area: the general field or domain (e.g., software, mechanical, biotech, chemical, electrical) to help route the disclosure to the right specialist.
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.
- 9d ago First seen · 163 lines · 39 tokens per session scan A f262d3f7840f
Invention Disclosure Intake is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 3,082 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
licensing-brief-writer
Writes a brief summarising the licensing requirements for using a specific piece of music, archive footage, photograph, or other third-party content in a media project — including what licences are needed, who to approach, and what terms to request.
Code Patent Validator
Turn your code scan findings into search queries — research existing implementations before consulting an attorney. NOT legal advice.
Patent Validator
Turn your concept analysis into search queries — research the landscape before consulting an attorney. NOT legal advice.
legal-research
A legal research skill for finding and analysing laws and court cases, including similar cases. It requires access to a reliable legal research database before producing a formal report.
document-fill
A document-filling assistant that uses a supplied template and case files to fill in forms, contracts, or legal documents. It also reports where each filled value came from and which details are missing.
contract-review
A contract-review workflow for agreements governed by Chinese law, United States law, or both. It examines clauses one by one and produces a list of legal-risk questions, with an optional marked-up Word document.