Borrowing it
Nothing to install: this file belongs to w1ne/kernelCAD-web. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/w1ne/kernelCAD-web/develop/AGENTS.mdgit clone --depth 1 https://github.com/w1ne/kernelCAD-webWrote 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/instructions/w1ne/kernelcad-web/agents-md)<a href="https://agentmods.dev/instructions/w1ne/kernelcad-web/agents-md"><img src="https://agentmods.dev/badge/instructions/w1ne/kernelcad-web/agents-md/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/instructions/w1ne/kernelcad-web/agents-md"><img src="https://agentmods.dev/badge/instructions/w1ne/kernelcad-web/agents-md.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 | $0.00350 | $0.00350 |
| Opus 5.5 | $0.00140 | $0.00140 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
kernelCAD-web AGENTS.md 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 14d 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.
What it actually says
Agent instructions
Read CLAUDE.md for repository conventions and docs/DEPLOY.md before deployment.
For every new or materially changed feature/tool:
- Check current official websites, documentation and demonstrations of comparable workflows before design or implementation. Record dated comparisons privately in kernelCAD-private; keep public artifacts framed as native kernelCAD behavior.
- Check the current kernelCAD website and existing source to avoid duplicate features. Update the relevant documentation/example and verify its public page after deployment.
- Create a small, readable MP4 demo of the actual feature workflow and result. Retain source, invocation/settings and verification evidence, inspect the video, and link the bundle from the feature's handoff. This applies to individual features/tools, including minor changes, analysis and distribution work.
- Keep replay, simulation, local validation, deployed behavior and hardware acceptance distinct in demo captions and completion claims.
Before browser work inspect and reuse an already-running Chrome/Chromium or CDP session and its login/profile. A missing automation connection does not justify a duplicate browser. Give attachment helpers a fixed lifetime and idle timeout; stop only their owned processes after each check and keep the user's browser running.
Commercial source boundary
This repository owns reusable CAD/kernel/tooling and the generic renderer. Hosted product UI, billing/checkout/entitlements, supplier quotes/routing/integrations, commissions, commercial orchestration and proprietary manufacturing policy belong in private repositories, including their tests, fixtures and strategy. Mixed modules stay private until reusable geometry is separated. Audit both source and built npm artifacts; do not restore product deployment workflows or package exports here.
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.
- 14d ago Changed · +4 lines · +88 tokens per session cd96860ef245
- 25d ago First seen · 24 lines · 262 tokens per session scan A f70fabdeb4ba
kernelCAD-web AGENTS.md is an instructions file published in the GitHub repository w1ne/kernelCAD-web (35 stars, last pushed today), licensed MIT. It adds 350 tokens to every session, about $0.0014 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 2026-10-12.
kernelCAD-web AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kernelCAD-web AGENTS.mdw1ne/kernelCAD-web | Instructions file | 35 | today | MIT | A | 350 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |