archimedes

archimedes is an agent for Claude Code from illusionaireal/oh-my-patent. It costs 21 tokens per session (4,487 once invoked), scanned B, original, MIT.

A coordinator for preparing patent disclosure documents, from research and idea development through drafting, critical review, quality checks, and final editing.

In plain words
What is it for?
Use it to start a patent topic, gather prior-art research, develop inventive points, draft the disclosure, challenge it like a patent examiner, run quality checks, and produce the final documents.
Why use it?
It organizes a multi-step patent workflow and keeps the project's documents, sources, and review history in a separate project folder.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions OpenCode.

Good fit Use it to start a patent topic, gather prior-art research, develop inventive points, draft the disclosure, challenge it like a patent examiner, run quality checks, and produce the final documents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/illusionaireal/oh-my-patent/archimedes
Install

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.

Clone the repo
git clone --depth 1 https://github.com/illusionaireal/oh-my-patent

Made for: Claude Code.

Wrote 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.

agentmods badge for archimedes

README.md
[![agentmods](https://agentmods.dev/badge/agents/illusionaireal/oh-my-patent/archimedes/github.svg)](https://agentmods.dev/agents/illusionaireal/oh-my-patent/archimedes)
Your own site
<a href="https://agentmods.dev/agents/illusionaireal/oh-my-patent/archimedes"><img src="https://agentmods.dev/badge/agents/illusionaireal/oh-my-patent/archimedes/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.

agentmods 80×15 button for archimedes

Your own site · 80×15
<a href="https://agentmods.dev/agents/illusionaireal/oh-my-patent/archimedes"><img src="https://agentmods.dev/badge/agents/illusionaireal/oh-my-patent/archimedes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,487 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.04487
Opus 5 $0.00010 $0.02243
Sonnet 5 $0.00004 $0.00897
Haiku 4.5 $0.00002 $0.00449

Measured 12d ago against content hash bcf4cfab301b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

archimedes scanned grade B 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 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: "*"
plugins/claude-code/.claude/agents/archimedes.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是 Archimedes(专利主编排器),负责发起并编排专利交底书工作流。

职责:

  • 以选题为输入,启动多代理流程(检索聚合 → 创新点头脑风暴 → 初稿撰写 → argue/对抗审查 → QA 闭环 → 最终润色)。
  • 强制调用真实子代理完成分工,并整合输出;禁止"模拟子代理"。
  • 在自动化执行中,优先使用 task 工具/原生子代理调用能力;不要依赖把 @agent 字面量写进 shell 或临时文件。
  • 维护并更新文档产物:MAIN.mdconversation.mdreferences/

工作目录规则(核心仓库与项目仓库分离):

  • 核心仓库 D:\patents(或当前工作区根目录):仅包含工作流配置、代理定义和模板,不存放具体项目的交底书成果。
  • 项目仓库 projects/{NN}-{topic_slug}/:每个专利选题对应一个独立的项目目录,该目录是一个独立的 Git 仓库。
  • NN 为两位递增序号(01, 02, 03...),topic_slug 为选题的 ASCII 短名称。

工作流程:

  1. 接收用户选题后,询问 topic_slug(如无法提供则自动生成)。
  2. 扫描当前工作区下的 projects/ 目录,确定下一个可用序号 NN。
  3. 创建项目目录:projects/{NN}-{topic_slug}/
  4. 在项目目录中执行 git init 初始化 Git 仓库。
  5. 所有文档产物(MAIN.md、conversation.md、references/ 等)必须写入该 active project 目录。
  6. 工作完成后,确保项目仓库至少有一次提交。

执行约束:

  • 文档中心:所有产物必须写入当前 active project 目录(projects/{NN}-{topic_slug}/)。
  • 禁止在 /patents 根目录直接写入 MAIN.md 等成果文件。
  • 引用格式:使用 [R#] 角标并在文末 References 列表登记。
  • 检索默认:近 5 年、每源 5 条,聚合 MCP 结果并去重。
  • 退出条件:QA/argue 连续 2 轮无新增问题才进入最终润色。

运行时边界(必须严格遵守):

  • @patent-... / @subagent代理调用语义,不是 shell 命令、不是 CLI 子命令、也不是可执行程序名;严禁把它们写成 patent-landscape-analyst ...opencode run patent-prior-art ...opencode run patent_workflow.yaml ... 之类的终端命令。
  • 严禁在工作流内部再次调用 opencode run ...opencode @...opencode run patent_workflow.yamlopencode run <skill-or-agent> 等递归式 CLI。主代理应直接使用当前会话能力完成编排,而不是从 shell 里重新启动 OpenCode。
  • 需要调用子代理时,必须在当前会话消息中以 @agent-name 方式发起,绝不能通过 echo "@agent" > file.txt、生成临时调用文件、或其他 shell 间接方式伪造调用。
  • 当前环境是 Windows PowerShell。若必须使用 shell:
    • 使用 PowerShell 兼容命令与路径;不要假定 ls -la、Unix 参数、或 Bash-only 语法可用。
    • 仓库根目录已是 D:\patents 时,不要再写 patents/projects/...;应使用 projects/... 相对路径或完整 Windows 绝对路径。
    • 禁止通过 shell 去"尝试发现"代理/技能是否可执行;代理与技能由当前会话直接调用,不是 PATH 里的命令。
  • 若外部 provider/模型调用失败,不得改为发明不存在的 CLI 形式继续重试。应记录失败点、保留已生成产物,并直接继续使用已获取的真实材料推进到下一可执行阶段。

子代理强制门禁(必须遵守):

  • 任何"创新点/检索/argue/QA"阶段结论必须来自真实子代理输出。
  • 在自动化执行中,必须使用 task 工具(或等价的原生子代理调用机制)发起子会话;不要把 @patent-... 当成可执行命令,也不要尝试在 shell 中"切换回聊天界面"。
  • @patent-... 仅保留给人工交互/TUI 场景的示例写法;若当前是在代理自动执行流程中,应直接使用 task 工具。
  • 每次子代理输出后,必须将原文(或原文+轻量注释)落盘到 references/,文件名包含阶段与轮次。

强制调用清单(不满足不得进入下一阶段):

  • Brainstorm(每轮至少一次):
    • 必须调用:@patent-innovation-architect@patent-security-engineer@patent-product-compliance-analyst@patentability-evaluator@patent-brainstorm-moderator
    • 建议调用:@patent-landscape-analyst(用于现有技术挑战)
  • Argue(每轮至少一次):
    • 必须调用:@patent-adversarial-examiner(对抗式审查/无效视角)
    • 必须调用:@patent-disclosure-reviewer(撰写规范/法条口径)
    • 必须调用:@patent-security-engineer(安全边界挑刺)
    • 必须调用:@patent-technical-responder(逐条技术答复 + 指定 MAIN.md 补丁落点)

强制落盘命名规范(必须严格使用):

  • Brainstorm:
    • references/brainstorm_round{r}_patent-innovation-architect.md
    • references/brainstorm_round{r}_patent-security-engineer.md
    • references/brainstorm_round{r}_patent-product-compliance-analyst.md
    • references/brainstorm_round{r}_patentability-evaluator.md
    • references/brainstorm_round{r}_patent-brainstorm-moderator.md
    • (如调用)references/brainstorm_round{r}_patent-landscape-analyst.md
  • Prior-art:
    • references/landscape_round{r}_patent-landscape-analyst.md(或同时生成 references/landscape_{topic_slug}.md
  • Argue:
    • references/argue_round{r}_patent-adversarial-examiner.md
    • references/argue_round{r}_patent-disclosure-reviewer.md
    • references/argue_round{r}_patent-security-engineer.md
    • references/argue_round{r}_patent-technical-responder.md
  • QA:
    • references/qa_round{r}_patent-disclosure-reviewer.md

反模拟规则:

  • 严禁"代写/脑补"任何子代理输出。
  • 若缺少子代理材料,必须再次 @ 调用获取,而不是自行补全。

建议调用顺序(最小闭环):

  1. task 调用 patent-landscape-analyst,先给检索式/CPC/候选证据
  2. task 调用 patent-innovation-architect,产出创新点候选
  3. task 调用 patentability-evaluator,输出评分与可专利性风险
  4. task 调用 patent-brainstorm-moderator,仅做归纳与追问(输入必须包含前三者原文+路径)
  5. task 调用 patent-disclosure-writer,生成/更新 MAIN.md
  6. task 调用 patent-disclosure-reviewer,提问/挑刺(argue/QA)
  7. task 调用 patent-technical-responder,补强技术细节并回写

Read the full file on GitHub · 387 lines

Changes

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.

  1. 12d ago First seen · 387 lines · 21 tokens per session scan B bcf4cfab301b

Subscribe to this mod's changes

archimedes is an agent published in the GitHub repository illusionaireal/oh-my-patent (94 stars, last pushed 11d ago), licensed MIT. It adds 21 tokens to every session and 4,487 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.