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/radix-ng/primitives/claude-mdgit clone --depth 1 https://github.com/radix-ng/primitivesWhat 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 | $0.09681 | $0.09681 |
| Opus 5 | $0.04841 | $0.04841 |
| Sonnet 5 | $0.01936 | $0.01936 |
| Haiku 4.5 | $0.00968 | $0.00968 |
Grade A, and why
primitives 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 yesterday.
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 — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radix NG Primitives — Claude Guide
Project knowledge
Detailed documentation lives in .claude/skills/project-knowledge/references/:
project.md— what the library is, audience, available primitivesarchitecture.md— tech stack, monorepo layout, composition primitives, DI context, CDK migrationpatterns.md— naming, new primitive checklist, signals conventions, testing, story patternsdeployment.md— CI/CD, release process, Storybook/docs buildsux-guidelines.md— demo styling system, semantic tokens, animation patterns
Read the relevant file before starting any non-trivial task. The sections below in this file are a quick-reference summary; the references/ files are the authoritative source.
Project overview
Angular port of headless UI primitives. This is a signals-first, headless component library — directives carry no styles; state is exposed via data-* attributes for consumers to style.
Reference priority: Base UI is the primary reference we align to — match its component APIs, naming, and behavior when designing or updating primitives. Radix UI was the original foundation of this library and remains a valid secondary reference to consult, especially for patterns Base UI doesn't cover.
- Monorepo: Nx 22, pnpm workspaces
- Angular: 21 / 22 (peer range
^21.0.0 || ^22.0.0; signals API:input(),model(),computed(),signal(),linkedSignal()) - TypeScript: 5.9
- Testing: Vitest + AnalogJS Angular Vite plugin +
@testing-library/angular - Storybook: 10 (
@storybook/angular+ AnalogJS vite plugin) - Styling in stories: Tailwind v4 (see "Stories & Storybook")
- Prefix:
rdx(selectors andexportAs) - Class prefix:
Rdx
Monorepo structure
packages/
primitives/ ← main Angular library (ng-packagr secondary entries)
<name>/
index.ts ← barrel exports + optional NgModule
ng-package.json ← secondary entry point {"lib":{"entryFile":"index.ts"}}
src/
<name>-root.directive.ts
<name>-<role>.directive.ts (or .ts without "directive" suffix for newer style)
__tests__/
<name>-root.directive.spec.ts
stories/
<name>.stories.ts
<name>.ts ← standalone story components
apps/
radix-storybook/ ← Storybook docs/examples; also the public site on radix-ng.com
radix-playground/ ← Angular playground app
radix-ssr-testing/ ← SSR smoke-test app
radix-perf-testing/ ← performance benchmark app
visual-regression/ ← Playwright visual and behavior specs
skills/ ← LLM consumer Agent Skills (generated from Storybook docs)
tools/
scripts/ ← build helpers (incl. skills bundle generator)
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.
- yesterday First seen · 406 lines · 9,681 tokens per session scan A ecea02e07370
primitives CLAUDE.md is an instructions file published in the GitHub repository radix-ng/primitives (269 stars, last pushed 7d ago), licensed MIT. It adds 9,681 tokens to every session, about $0.0484 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 instructions, from other repositories
core-web copilot-instructions.md
Copilot instructions for db-ux-design-system/core-web: All development instructions, build commands, validation steps, coding rules, and the pull request workflow are maintained in AGENTS.md at the repository root. Read that file first before starting any task.
core-web AGENTS.md
AGENTS.md instructions for db-ux-design-system/core-web, covering db ux design system v3 core web, working effectively, required prerequisites, bootstrap and setup and build and test.
ark CLAUDE.md
Instructions for chakra-ui/ark, covering ark ui - claude development guide, documentation structure, quick start, common commands and install dependencies.
fundamental-ngx AGENTS.md
Instructions for SAP/fundamental-ngx, covering angular 22+ development guidelines, persona, quick reference, essential commands and build/lint/test specific library.
fundamental-ngx CLAUDE.md
Instructions for SAP/fundamental-ngx, covering fundamental ngx, architecture, commands, build / lint / test a library and affected only (prefer this for validation).
openbridge-webcomponents watch-radial-instruments.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering watch & radial instruments, architecture overview, key principle: logic in watch.ts, instruments stay thin, shared sibling modules and layering & stacking pattern.