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/radix-ng/primitives/project-knowledgenpx skills add radix-ng/primitives --skill project-knowledgegit 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 | $0.00048 | $0.00701 |
| Opus 5 | $0.00024 | $0.00351 |
| Sonnet 5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
project-knowledge 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Knowledge
This skill provides access to project documentation that defines how this project works, how code should be written, and how features should be developed.
When to use
Activate this skill when you need to:
- Understand project architecture, tech stack, and data model
- Learn coding patterns, git workflow, and testing approach
- Check deployment setup, monitoring, and operational procedures
- Apply UX guidelines and design system
- Make technical decisions aligned with project standards
Core references
All documentation is in the references/ folder:
- project.md - Project overview, purpose, target audience, core features, scope boundaries
- architecture.md - Tech stack, project structure, dependencies, external integrations, data flow, data model (schema, migrations, sensitive data)
- patterns.md - Project-specific coding conventions, git workflow (branching, testing, security gates), testing & verification methods, business rules
- deployment.md - Deployment platform, environment variables, CI/CD triggers, rollback, monitoring & observability (logging, error tracking, health checks)
Optional references
- ux-guidelines.md - Demo styling system, semantic tokens, animation patterns, accessibility conventions for Storybook stories
- signal-forms-readiness.md - Angular Signal Forms conformance matrix per form control, collisions, and Angular-21 prep backlog
How to use
Read specific guides as needed for your task:
- Starting feature development - read project.md, architecture.md, patterns.md
- Implementing database changes - read architecture.md (Data Model section)
- Working on UI/UX - read ux-guidelines.md
- Setting up deployment - read deployment.md
- Creating branches or PRs - read patterns.md (Git Workflow section)
- Investigating logs or errors - read deployment.md (Monitoring section)
- Working with domain logic - read patterns.md (Business Rules section)
- Reporting a misuse / adding a dev-mode warning, error, or host-element check to a primitive - read patterns.md (Dev-mode diagnostics section). Always go through
core/src/dev/diagnostics.ts(rdxDevWarning/rdxDevError/rdxCheckTriggerElement/rdxCheckLabelElement) with a stable[rdx:<primitive>/<slug>]code — never a fresh ad-hocconsole.warn/throw - Adopting Angular Signal Forms or touching form controls - read signal-forms-readiness.md
What ships with it
6 files 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.
- yesterday First seen · 53 lines · 48 tokens per session scan A 8f8c5953be20
project-knowledge is a skill published in the GitHub repository radix-ng/primitives (269 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 701 once invoked, about $0.0002 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
create-db-component
Creates a new DB UX Design System component with Mitosis source, SCSS, typed model, and Playwright tests.
modify-db-component
Modifies an existing DB UX Design System Mitosis component (add variants, update props, change styles).
test-component
Runs, analyzes, and fixes Playwright and accessibility tests for a specific DB UX component.
implement-component
Implements production-ready UI using DB UX Design System v3 components, tokens, and icons with a discovery-first approach.
migrate-to-v3
Migrates legacy DB UI v2 code (cmp-, elm-, rea- classes, Web Components, db-color- tokens) to DB UX Design System v3.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…