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 instructions/layzeedk/angular-typechecker/claude-mdgit clone --depth 1 https://github.com/LayZeeDK/angular-typecheckerWhat 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 | $0.07927 | $0.07927 |
| Opus 5 | $0.03964 | $0.03964 |
| Sonnet 5 | $0.01585 | $0.01585 |
| Haiku 4.5 | $0.00793 | $0.00793 |
Grade A, and why
angular-typechecker CLAUDE.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 2d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
Project
angular-typechecker
angular-typechecker is an Nx plugin that type-checks Angular projects -- applications, libraries (local/non-buildable, buildable, and publishable), and unit-test (spec) tsconfigs -- the way ngc --noEmit -p <tsconfig> would, but completely and decoupled from building or running tests. It runs the Angular compiler's full diagnostic set: TypeScript checks plus Angular template type-checking and extended diagnostics (NG8xxx). The first milestone (v0.0.1) ships a single Nx executor (typecheck) targeting Nx 23 + Angular 22 (TypeScript 6). It exists to give a fast static-check feedback loop for AI coding agents and CI pipelines.
Core Value: Deliver the complete Angular type-check (TypeScript + template type-check + extended diagnostics) for any project type without building the application or executing the tests -- faster, in isolation, and more completely than either the build's coupled check or a bare ngc --noEmit.
Why this matters (validated by Brandon Roberts' 2026-06-26 analysis): at scale the whole-program type-check is the dominant, separable cost of an Angular build (~15s standalone ngc --noEmit vs ~36s full esbuild build). Fast per-file compilers (AnalogJS fastCompile, the experimental Oxc compiler) and esbuild dev deliberately skip the type-check for speed and expect you to "run the type-check elsewhere"; the editor's Angular Language Service covers the live loop. angular-typechecker is that "elsewhere" for headless/CI/agent loops -- Nx-native, cacheable, and runnable per project.
Distinct from Nx's built-in @nx/js typecheck target (plain tsc/tsgo): Angular projects cannot use that fast path -- Angular lacks TypeScript project-references support -- and it would not surface Angular template type-check or extended (NG8xxx) diagnostics anyway. angular-typechecker is the Angular-aware whole-program no-emit type-check that fills that gap.
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.
- 2d ago First seen · 246 lines · 7,927 tokens per session scan A d9726c9a97c7
angular-typechecker CLAUDE.md is an instructions file published in the GitHub repository LayZeeDK/angular-typechecker (10 stars, last pushed 24d ago), licensed MIT. It adds 7,927 tokens to every session, about $0.0396 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 2026-08-31.
Other instructions, from other repositories
tevm CLAUDE.md
Claude Code instructions for evmts/tevm, covering tevm monorepo commands and style guide, project overview, forking implementation, json-rpc support and commands.
moss AGENTS.md
Instructions for D-Robotics/moss, covering agents.md, 仓库身份, 文档所有权与阅读顺序, 代码规范执行摘要（必须遵守） and 第一次进入仓库.
platform AGENTS.md
Instructions for dashpay/platform, covering repository guidelines, project structure & module organization, architecture, technology stack and key components.
agnix typescript.instructions.md
Instructions for agent-sh/agnix, covering typescript instructions and guidelines.
copperhead CLAUDE.md
Instructions for copperheadhq/copperhead, covering claude.md, what this repo is, sources of truth, workflow (openspec) and architecture (per spec.md §2).
chatgpt-vue3-light-mvp AGENTS.md
Instructions for pdsuwwz/chatgpt-vue3-light-mvp, a project described as: 💭 一个可二次开发 Chat Bot 单轮对话 Web 端 MVP 原型模板, 基于 Vue 3, Vite8, TypeScript, Naive UI, Pinia(v3), UnoCSS 等主流技术构建, 🧤简单集成大模型 API, 采用单轮 AI 问答对话模式, 每次提问独立响应, 无需上下文, 支持 SSE 打字机效果流式输出, 集成 markdown-it Mermaid/KaTex/LaTex 公式高亮预览, 星火, 智谱, 硅基流动, Deepseek…