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 commands/joncik91/ucai/initgit clone --depth 1 https://github.com/Joncik91/ucaiWhat 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 | $0.00012 | $0.01453 |
| Opus 5 | $0.00006 | $0.00727 |
| Sonnet 5 | $0.00002 | $0.00291 |
| Haiku 4.5 | $0.00001 | $0.00145 |
Grade A, and why
init 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Initialization
You are setting up a project to work effectively with Claude Code. Your goal is to analyze the codebase and generate accurate, useful project guidelines — not a framework config dump.
Core Principle
CLAUDE.md should contain project facts that Claude doesn't already know: conventions, architecture decisions, build commands, and patterns specific to this codebase. Nothing generic.
Skill Loading — MANDATORY
Before starting Phase 2A, you MUST load the ucai:architect skill — project initialization is architecture analysis work.
- Load the skill using the Skill tool:
Skill(ucai:architect) - If the project is clearly a specific domain (backend API, frontend app, etc.), also load the matching skill:
Skill(ucai:backend),Skill(ucai:frontend), etc. - Apply the skill's guidance when analyzing the project and drafting CLAUDE.md
You MUST load at least one skill before proceeding. State which skill(s) you loaded and why.
Phase 1: Detection (MANDATORY — do this BEFORE anything else)
Goal: Determine whether this is an existing project or an empty/new one.
Project path: $ARGUMENTS (default: current directory)
Actions:
- Create a todo list to track progress
- Check for
.claude/project.md. If found, read it — this provides project vision, tech stack, and constraints as context for analysis. - Use Glob to search for source code files:
**/*.{js,ts,jsx,tsx,py,go,rs,java,rb,php,cs,cpp,c,swift,kt}and package manifests:{package.json,pyproject.toml,Cargo.toml,go.mod,Gemfile,composer.json,*.csproj,pom.xml,build.gradle} - Decision gate — you MUST follow this strictly:
- If zero source code files AND zero package manifests are found → go to Phase 2B (do NOT launch scanners)
- If source code or package manifests exist → go to Phase 2A
IMPORTANT: Do NOT launch project-scanner agents on an empty project. They will waste tokens scanning nothing.
Phase 2A: Analysis (Existing Project)
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 · 148 lines · 12 tokens per session scan A ca37454f55e6
init is a command published in the GitHub repository Joncik91/ucai (29 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 1,453 once invoked, about $0.0001 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 commands, from other repositories
f5-gate
Quality gate management with evidence collection.
f5-classify
Classify input files by type using content-first analysis, detect gaps, and generate coverage declaration.
f5-implement
Implement features and fix bugs with traceability.
f5-design
Generate design documents and specifications (D1-D4).
f5-import
Import documents - single, batch, analyze, or schema management.
f5-agent
Manage AI agents, personas, and get smart suggestions.