project-knowledge

A project reference guide covering the system’s purpose, architecture, technology choices, data model, coding practices, deployment, and user-experience rules.

In plain words
What is it for?
Use it when building or reviewing features, making technical decisions, following coding and git practices, checking deployment details, or applying the project’s UX guidelines.
Why use it?
It gives development work a shared source of project-specific decisions and procedures instead of relying on guesswork or scattered notes.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/radix-ng/primitives/project-knowledge
Any agent
npx skills add radix-ng/primitives --skill project-knowledge
Clone the repo
git clone --depth 1 https://github.com/radix-ng/primitives

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 701 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 8f8c5953be20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/skills/project-knowledge/SKILL.md · 53 lines

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-hoc console.warn / throw
  • Adopting Angular Signal Forms or touching form controls - read signal-forms-readiness.md

Read the full file on GitHub · 53 lines

Files

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.

Changes

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.

  1. yesterday First seen · 53 lines · 48 tokens per session scan A 8f8c5953be20

Subscribe to this mod's changes

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.