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 agentmods add skills/internlm/wildclawbench/architecturenpx skills add InternLM/WildClawBench --skill architecturegit clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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/internlm/wildclawbench/architecture)<a href="https://agentmods.dev/skills/internlm/wildclawbench/architecture"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/architecture.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.01346 |
| Opus 5 | $0.00007 | $0.00673 |
| Sonnet 5 | $0.00003 | $0.00269 |
| Haiku 4.5 | $0.00001 | $0.00135 |
Grade A, and why
Architecture 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detect Level, Adapt Everything
- Context reveals level: vocabulary, technical depth, professional credentials
- When unclear, ask about their role before giving specific guidance
- Ask project location for code and zoning questions; requirements vary by jurisdiction
For Homeowners: Clear Expectations
- Translate drawings into plain language — explain floor plans, elevations, sections; what symbols mean; how to read scale notations
- Explain design phases — Schematic Design → Design Development → Construction Documents → Bidding → Construction Administration; what happens when
- Demystify fee structures — percentage of construction, hourly, fixed fee; what's included vs extra; contract red flags
- Clarify permit thresholds — structural changes, electrical, plumbing, adding space need permits; cosmetic updates usually don't; verify locally
- Set budget reality — 15-20% contingency rule; why estimates differ from bids; common surprises (soil, asbestos, code upgrades); soft vs hard costs
- Prepare for realistic timelines — permit review 2-12+ weeks; design takes longer than expected; construction almost always extends
- Decode terminology on demand — setback, FAR, egress, bearing wall, as-built, punch list with context for why it matters
- Guide productive communication — how to give useful feedback; questions before hiring; when to push back vs trust professional
For Students: Design and Rigor
- Explain principles with visual language — reference built examples; describe how principles manifest physically; never speak abstractly
- Cite movements with precision — time period, seminal buildings, key architects, theoretical context; students need citation accuracy
- Support technical drawing conventions — orthographic projection, axonometric, perspective; lineweights, notation, scale; match professional standards
- Guide precedent analysis — program, site response, structure, circulation, spatial sequence, materiality, theoretical positioning
- Use studio vocabulary — parti, poché, datum, threshold, hierarchy, procession, figure-ground, phenomenology; language of architecture juries
- Support thesis-level theory — Vitruvius to Venturi to Koolhaas; phenomenologists like Pallasmaa and Zumthor; help position work in frameworks
- Distinguish concept from resolution — early stage needs conceptual provocation; later stages need technical resolution; ask where in process
- Respect drawing as thinking — encourage sketching and diagramming; prompt drawing through problems rather than just discussing
What ships with it
1 file 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.
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 · 79 lines · 14 tokens per session scan A f0ee72367a78
Architecture is a skill published in the GitHub repository InternLM/WildClawBench (516 stars, last pushed 19d ago), licensed MIT. It adds 14 tokens to every session and 1,346 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
code-walkthrough
与用户共同阅读 Neeko 代码，逐层讲解 Tauri 应用架构与跨端数据流。支持三域分层模式（Rust 后端 / React 前端 / 跨端桥接）和调用链追踪模式（含跨端追踪）。主动发现 dead code、设计偏差、类型不一致、迁移遗漏，但不修改代码。Use when user wants to walkthrough code, understand architecture, trace call chains, review a module's structure, or says "过代码" / "walkthrough" / "walk me through" / "zoom out".
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
journey-template
Create new agentic journeys from app ideas. Generates README.md (learner walkthrough), PLAN.md (AI-readable spec), and app-specific skills for OSS deployments. Supports any stack (Node.js, Python, .NET, Java, Swift, Kotlin) and Azure service (Container Apps, AKS, Functions, App Service). USE FOR: new journey, scaffold…
naga-config
Naga 自身配置管理技能。用于查看和修改 Naga 系统设置、添加 MCP 工具服务、导入自定义技能、搜索可用 MCP 工具。当用户要求修改设置、添加工具或技能时使用此技能。.
journey-runner
Run an agentic journey end-to-end: preflight the host, extract prompts, execute them in an isolated workspace, build, deploy to Azure, verify with real requests and screenshots, and clean up only owned resources. USE FOR: test a journey, run a journey end-to-end, validate journey prompts, deploy a journey to Azure…
naga_control
通过 agentType: "nagacontrol" 调用，直接控制 Naga 自身的运行状态和配置。.