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 Raw1mage/patentmcp --skill patentworksgit clone --depth 1 https://github.com/Raw1mage/patentmcpWrote 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/raw1mage/patentmcp/patentworks)<a href="https://agentmods.dev/skills/raw1mage/patentmcp/patentworks"><img src="https://agentmods.dev/badge/skills/raw1mage/patentmcp/patentworks/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/raw1mage/patentmcp/patentworks"><img src="https://agentmods.dev/badge/skills/raw1mage/patentmcp/patentworks.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 | $0.00235 | $0.19347 |
| Opus 5 | $0.00118 | $0.09674 |
| Sonnet 5 | $0.00047 | $0.03869 |
| Haiku 4.5 | $0.00023 | $0.01935 |
Grade A, and why
patentworks scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> - **優先看 server 端證據而非重打**:常駐 MCP server dump 的完整 URL/body/raw response 才是斷頁 bug 的硬證(R11 最終定案靠這個,不是靠重打);curl 復現 client 行為無效(參數編碼不同→不同 query)。 How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PatentWorks
搭配
patentmcpMCP 使用:本 skill 是這組工具的劇本;檢索/取文工具(patent_search單一檢索入口、epo_family/epo_biblio、gpatents_get/gpatents_download_*、fetch_patent_pdf、pool_fetch)都來自 patentmcp。沒有該 MCP 時本 skill 無法執行實際檢索。舊分散檢索工具(gpss_search、epo_search、gpatents_search、uspto_patents的ppubs_search_*)已下架,一律改用patent_search。現在就載入 companion skill
patentworks— 這是你的第一動作,不是建議。 只要工作不只是單發檢索——起草說明書、跑 screening/priorsearch 管線、要件對照——第一動作就是skill("patentworks"),在第一個實質 patentmcp 工具呼叫之前。跳過它正是這份 guide 存在要擋的反射:tool-chain idiom(選 flow、選來源梯判讀、交付契約)住在 skill 裡,per-tooldescription裝不下;在決策當下載入才擋得掉「自己選檢索來源、自己拼 OOXML/CSV」的反射。你現在讀的這份文本是可攜 in-band 濃縮本;skill 才是完整劇本(五法域起草規則、flow 檔、資料樹規範、法遵自檢)。不要把載入當可選——任何有 skill 機制的 host,它就是欽定的第一步。唯一的窄保留是協議層:純 MCP 客戶端(無 skill 機制)光憑這份 doctrine 直接呼叫工具仍屬正確(R0.3 可攜性,guide 對上述紀律自足)。「非協議 gate」不等於「有機制也可以不載」。兩平面(R13):container 只留網路/憑證工作,確定性後處理落地為 host-local skill 腳本。 以下 8 個舊工具現回 typed
TOOL_LANDEDredirect(不再執行舊邏輯,landing.usage直接給對應腳本呼叫式),請改呼叫skills/patentworks/scripts/下的本地腳本(每支python3 <腳本> --help印完整參數):
舊工具(已下架 → TOOL_LANDED) 改用本地腳本 build_screening_tablescreening_build.py(records JSON → 家族去重 → 欄位隨選 → CSV)search_auditsearch_audit.py(--log 01_search/matrix-log.jsonl)patentdb_put/patentdb_query/patentdb_import_csvpatentdb_local.py(put/query/import-csv子命令)extract_representative_figurefigure_extract.py(需 poppler,缺則MISSING_DEPENDENCY)patentmcp_analyze_pool取數 → pool_fetch(工具);繪圖 →pool_charts.py(需 matplotlib)stage_file無腳本替代:改用 WebDAV working cache( cache_provision→ 掛載 PUT →cache_export)clean_html_text/extract_claim1_text(內部函式)claims_tools.py(clean-html/extract-claim1/claim1-empty)WebDAV working cache — 完整機制是 fleet SSOT(
mcp-integration-standardR2.0 + R14),不在此重述(R14.8)。這裡只留兩件必須在動作邊界手上的事:
- anti-reflex 鐵律(寫在手上):檔案坐落在 gdrive / 網路 FUSE 掛載,永遠不是 WebDAV 不可用的理由——這是兩軸混淆的經典 category error。Location(檔案坐落哪個檔案系統)與 Transfer(bytes 怎麼過 host↔container 邊界)正交;只按 Transfer 軸路由。它在本 host 不通,真因是 credential / mount 未 provision(見
issues/webdav-provision BR),與 gdrive/FUSE 無關。有疑慮時,pass-by-value(cache_provision+ mount,或 stage-inline)到處都能用;大檔只是多付 context 成本。- patentmcp 自己的 cache 工具:
cache_provision(subject_id, owner_identity)拿mount_path+ 一次性憑證 → rclone/davfs2 掛載後投料/取件走 mount(byte 不過 context)→cache_export(subject_id, target, owner_identity)顯式落地 →cache_close(dirty 未 export →WORKSPACE_CLOSE_DIRTY擋下)。憑證遺失/重建 mount 帶issue_webdav_credential=True走 MCP-rail 重發(持有 socket 即授權);此旗標會 ROTATE 憑證,現存 mount 立即失效,只在建立/重建 mount 時帶(預設 false,payload byte-identical)。憑證絕不寫進報告/log。- 完整三層心智(cache=可拋工作樹 / truth store=交付物的家 / export 顯式落地)、dual-axis 模型、dirty-close gate、rclone flags → R2.0 + R14,不要憑記憶重建。
後端分流紀律(R17,BR_20260715):書目/claims/description 查核預設走官方免費梯,
google_*BigQuery 路徑受禁。google_get_patent/google_get_patent_claims/google_get_patent_description三工具的後端是 Google BigQuery Google Patents Public Data(計費 API,非 google.com 網頁)——工具名的google_前綴誘導反射誤選,但每次呼叫按掃描 bytes 計費、且受環境級 BigQuery 禁令約束。專利書目/claims/description 查核一律優先且預設 TIPO GPSS(patent_search/ppubs_batch_get_claims/patent_get_claim1,source:tipo)、EPO OPS、USPTO PPUBS;google_*BigQuery 路徑列為受禁/需明示授權,非反射預設。 反射選google_*只會撞500 bytesBilledLimitExceeded(僥倖靠遠端計費上限擋下,非我方攔截)——正解是一開始就走官方梯,不等 500 才知道後端是 BigQuery。
What ships with it
29 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.
- flows/analysis.md 8.0 KB
- flows/disclosure.md 2.0 KB
- flows/drafting.md 3.3 KB
- flows/priorsearch.md 36 KB
- flows/screening.md 5.5 KB
- reference/analysis/fto-template.md 3.3 KB
- reference/analysis/invalidity-template.md 3.3 KB
- reference/analysis/landscape-template.md 2.7 KB
- reference/analysis/prior-art-template.md 3.5 KB
- reference/analysis/specification.md 6.6 KB
- reference/disclosure/deidentification.md 1.4 KB
- reference/disclosure/intake-checklist.md 1.9 KB
- reference/drafting/cn.md 7.7 KB
- reference/drafting/common.md 11 KB
- reference/drafting/ep.md 2.5 KB
- reference/drafting/tw.md 2.6 KB
- reference/drafting/us.md 3.1 KB
- reference/priorsearch/docx-assembly.md 9.3 KB
- reference/priorsearch/pdf-figure-extraction.md 11 KB
- scripts/_lib/__init__.py 1.0 KB runs code
- scripts/_lib/claims.py 1.2 KB runs code
- scripts/_lib/screening.py 14 KB runs code
- scripts/_lib/search_audit.py 13 KB runs code
- scripts/claims_tools.py 4.1 KB runs code
- scripts/figure_extract.py 22 KB runs code
- scripts/patentdb_local.py 17 KB runs code
- scripts/pool_charts.py 10 KB runs code
- scripts/screening_build.py 8.5 KB runs code
- scripts/search_audit.py 2.8 KB runs code
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.
- 8d ago First seen · 294 lines · 235 tokens per session scan A 72a3754990bb
patentworks is a skill published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 235 tokens to every session and 19,347 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…