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 raja21068/AutoResearch --skill claims-draftinggit clone --depth 1 https://github.com/raja21068/AutoResearchWrote 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/raja21068/autoresearch/claims-drafting)<a href="https://agentmods.dev/skills/raja21068/autoresearch/claims-drafting"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/claims-drafting/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/raja21068/autoresearch/claims-drafting"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/claims-drafting.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 | $0.00053 | $0.02520 |
| Opus 5 | $0.00026 | $0.01260 |
| Sonnet 5 | $0.00011 | $0.00504 |
| Haiku 4.5 | $0.00005 | $0.00252 |
Grade A, and why
claims-drafting 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.
This is a copy
97% identical to claims-drafting — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claims Drafting: The Core Patent Skill
Draft patent claims based on: $ARGUMENTS
This is the most critical skill in the patent pipeline. Claims define the legal scope of protection -- everything else (specification, figures, abstract) exists to support and enable the claims.
Constants
REVIEWER_MODEL = gpt-5.4— External examiner for claim quality reviewMAX_CLAIM_REVISION_ROUNDS = 3— Maximum revision iterationsCLAIM_STYLE = "auto"—US(Jepson or open),EP(two-part mandatory),CN(two-part),auto(detect from jurisdiction)MIN_INDEPENDENT_CLAIMS = 2— Typically method + system. For utility model (实用新型): apparatus/device only, NO method claims.MAX_TOTAL_CLAIMS = 20— Practical limit (USPTO includes 20 in base fee)PATENT_TYPE = "invention"—invention(发明专利) orutility_model(实用新型, apparatus claims only)
Inputs
patent/INVENTION_DISCLOSURE.md— structured invention with core/supporting/optional featurespatent/PRIOR_ART_REPORT.md— prior art to avoidpatent/NOVELTY_ASSESSMENT.md— novelty analysis with suggested amendments- Target jurisdiction from invention disclosure or
$ARGUMENTS
Shared References
Load ../shared-references/patent-writing-principles.md for claim drafting principles, antecedent basis rules, and common pitfalls.
Load ../shared-references/patent-format-cn.md for CN claim format (其特征在于).
Load ../shared-references/patent-format-us.md for US claim format (comprising, means-plus-function).
Load ../shared-references/patent-format-ep.md for EP two-part form (characterised in that).
Workflow
Step 1: Determine Claim Style and Patent Type
Based on patent type and jurisdiction:
If PATENT_TYPE = utility_model (实用新型):
- CN jurisdiction ONLY
- Apparatus/device claims ONLY — no method, no product-by-process
MIN_INDEPENDENT_CLAIMS = 1(single apparatus claim is sufficient)- Claim format: "1. 一种[主题]，其特征在于，包括：[组件描述]。"
Based on target jurisdiction:
| Jurisdiction | Claim Style | Characterising Phrase | Preamble Format |
|---|---|---|---|
| CN | Two-part (两部式) | 其特征在于 | 一种...的方法/装置，包括： |
| US | Open (preferred) | comprising | A method for..., comprising: |
| EP | Two-part (mandatory) | characterised in that | A method for..., comprising [known], characterised in that [inventive] |
| ALL | Draft CN + US + EP | All of the above | All of the above |
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 · 227 lines · 53 tokens per session scan A 5fe40ea767cf
claims-drafting is a skill published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 2,520 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to claims-drafting, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
content-refinement-agent
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate…
literature-review-agent
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to…
agent-research-aggregator
Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimentallog.md). TRIGGER when the user says…
paper-orchestra
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper…
section-writing-agent
Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…
plotting-agent
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…