ucai CLAUDE.md

ucai CLAUDE.md is an instructions file for Claude Code from Joncik91/ucai. It costs 2,628 tokens per session, scanned A, original, MIT.

Development instructions for Ucai, a Claude Code plugin that adds structured task tracking and execution rules. It includes commands, agents, hooks, skills, automated formatting, test execution, and workflows for moving from a specification to a pull request.

In plain words
What is it for?
Use them when developing Ucai, running its checks, changing commands or hooks, working on its task-enforcement engine, or maintaining its TDD and review workflows.
Why use it?
They help contributors understand the plugin's architecture and keep its enforcement and automation behavior consistent. They also document the supported runtime, platform, and development setup.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

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 instructions/joncik91/ucai/claude-md
Clone the repo
git clone --depth 1 https://github.com/Joncik91/ucai

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ucai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joncik91/ucai/claude-md.svg)](https://agentmods.dev/instructions/joncik91/ucai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/joncik91/ucai/claude-md"><img src="https://agentmods.dev/badge/instructions/joncik91/ucai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,628 This file is loaded in full into every session.
When invoked 2,628 The same file — it is already loaded in full.
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 5.1 $0.02628 $0.02628
Opus 5 $0.01314 $0.01314
Sonnet 5 $0.00526 $0.00526
Haiku 4.5 $0.00263 $0.00263

Measured 6d ago against content hash 5e4991af39f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ucai 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 6d 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.

CLAUDE.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ucai — Use Claude Code As Is

Overview

A Claude Code plugin that leverages native architecture — commands, agents, hooks, and skills — exactly as Anthropic designed them. v2.3 adds discipline layers on top of v2.2's enforcement engine: pre-flight requirement audits before code is written, per-issue failure-mode analysis on every review, design-pivot clauses, and strict author/reviewer separation for tests with anti-gaming verdicts aligned with the Pragma detector. v2.2 added the never-forget enforcement engine — programmatic phase enforcement via ContingencyEngine with dependencies, logic gates, shadow tasks, and audit trail. v2.0 added autonomous execution — /ship (zero-gate spec-to-PR pipeline), /bootstrap (infrastructure scaffolding), PostToolUse auto-formatting, deterministic test execution, and lessons consolidation. Built on the Cherny methodology: persistent task tracking, self-improvement loop, TDD integration, and elegance checkpoints.

Tech Stack

  • Runtime: Node.js 18+ (CommonJS, zero external dependencies)
  • Plugin format: Markdown (YAML frontmatter) + JSON configs
  • Platform: Windows/Linux/macOS, CI matrix: Node 18 × 20 on ubuntu + windows

Development Commands

No build step. Validation only:

# Local dev
claude --plugin-dir ./ucai

# JSON syntax
node -e "JSON.parse(require('fs').readFileSync('.claude-plugin/plugin.json', 'utf8'))"
node -e "JSON.parse(require('fs').readFileSync('hooks/hooks.json', 'utf8'))"
node -e "JSON.parse(require('fs').readFileSync('.claude-plugin/marketplace.json', 'utf8'))"

# JS syntax (all handlers + scripts)
for file in hooks/handlers/*.js scripts/*.js; do node -c "$file" || exit 1; done

# Smoke test
output=$(node hooks/handlers/sessionstart-handler.js)
node -e "const o=JSON.parse(process.argv[1]); if(!o.hookSpecificOutput) process.exit(1)" "$output"

Architecture

Layers

  • commands/ — Orchestration: phased workflows with user approval gates. Write/Edit only here.
  • agents/ — Execution: read-only analysis workers, spawned in parallel via Task tool.
  • hooks/handlers/ — Lifecycle: context injection, state management, config protection.
  • skills/ — Knowledge: progressive disclosure domain expertise, loaded on-demand.
  • scripts/ — Utilities: setup-ship.js, detect-infra.js, run-tests.js, consolidate-lessons.js.
  • scripts/lib/never-forget/ — Vendored never-forget engine (ESM, zero deps): dependency validation, logic gates, shadow tasks, audit trail.

Read the full file on GitHub · 171 lines

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. 6d ago First seen · 171 lines · 2,628 tokens per session scan A 5e4991af39f7

Subscribe to this mod's changes

ucai CLAUDE.md is an instructions file published in the GitHub repository Joncik91/ucai (29 stars, last pushed 10d ago), licensed MIT. It adds 2,628 tokens to every session, about $0.0131 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.

Related

Other instructions, from other repositories