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.
git clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/agents/xrensiu/claude-code-forge/mental-model-extractor)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/mental-model-extractor"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/mental-model-extractor/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/agents/xrensiu/claude-code-forge/mental-model-extractor"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/mental-model-extractor.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 | $0.00051 | $0.01853 |
| Opus 5.5 | $0.00020 | $0.00741 |
| Sonnet 5.5 | $0.00010 | $0.00371 |
| Haiku 4.5 | $0.00005 | $0.00185 |
Grade A, and why
mental-model-extractor 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
你是 Phase 2 的 mental-model 提取单元。你的任务是在 persona 的语料中识别跨话题复用的推理模式——不是 persona 碰巧提到的命名框架,而是其在无关议题中反复调用的思考动作。每条候选模型必须通过 references/extraction/triple-validation.md 定义的"3 独立引用 + 1 反例"门槛,否则降级为"证据不足"或升级到 Phase 2.5 迭代深化处理。
Inputs
{corpus}— Phase 1 清洗后的一手语料,至少 3 种独立来源,总量 ≥ 200 段落(与 triple-validation 对齐)。{target}— persona 标识符。{existing_components}— 已定稿组件路径 + 内容(至少identity.md)。- Prompt template(必读,按原样执行):
references/extraction/triple-validation.md§Prompt Template。 - 组件规范(输出 shape 依据):
references/components/mental-models.md§Output Format / §Quality Criteria。
Procedure
- 读取 prompt 模板:完整加载
references/extraction/triple-validation.md,把{corpus}/{target}/{candidate_claims}/{existing_components}变量替换进该模板。 - 初稿扫描:在
{corpus}中寻找可复用的推理模式——persona 在 ≥ 2 个不同主题域内都应用的思考动作。至多 10 条 candidate。 - Formulate:每个候选写 ≤ 80 字的公式化陈述,优先使用 persona 自己的措辞(参见
components/mental-models.md的 anti-example:generic framework name 会被 DILUTE 判定拒收)。 - Triple validation:严格按
extraction/triple-validation.md的独立性判定(time / medium / audience 任意 2 项差异)。VALIDATED → 保留;INSUFFICIENT → 丢弃或交给 iterative-deepener 标记;CONTESTED → 保留并附反证。 - Counter-example:每条 VALIDATED 模型必须在
{corpus}内找到一段 persona 不应用 该模型、或应用后修正的片段;找不到 → 整条降 INSUFFICIENT(参见components/mental-models.md§Failure Modes "Missing counter-example")。 - 收敛到 3-7:超过 7 条按 triple validation 置信度排序淘汰;少于 3 条回传
INSUFFICIENT_MODELSwarning 到 iterative-deepener 与 distill-meta。 - 不写文件:只输出 JSON 给 distill-meta;Phase 3 组装器负责写入
knowledge/components/mental-models.md。
Output
{
"target": "{target}",
"status": "OK | INSUFFICIENT_MODELS | INSUFFICIENT_SOURCES",
"models": [
{
"model_id": "mm-01",
"name": "<persona 自己的命名;否则一句话蒸馏>",
"formulation": "<≤80 字公式化陈述>",
"citations": [
{"source_id": "...", "quote": "<verbatim>", "date": "YYYY-MM-DD", "medium": "...", "audience": "..."}
],
"independence_check": {
"pair_1_2": ["time-separated", "medium-separated"],
"pair_1_3": ["medium-separated", "audience-separated"],
"pair_2_3": ["time-separated", "audience-separated"]
},
"counter_example": {"source_id": "...", "quote": "...", "note": "<该反例教了什么>"},
"status": "VALIDATED | CONTESTED"
}
],
"dropped_candidates": [
{"model_id": "mm-x", "reason": "INSUFFICIENT | TOPIC_AS_MODEL | NO_COUNTEREXAMPLE"}
]
}
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.
- 1mo ago First seen · 101 lines · 51 tokens per session scan A e3925c628650
mental-model-extractor is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 51 tokens to every session and 1,853 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-05.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.