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/joncik91/ucai/claude-mdgit clone --depth 1 https://github.com/Joncik91/ucaiWrote 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.
[](https://agentmods.dev/instructions/joncik91/ucai/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 6d ago First seen · 171 lines · 2,628 tokens per session scan A 5e4991af39f7
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.
Other instructions, from other repositories
archeyes CLAUDE.md
Instructions for thisAAY/archeyes, covering archeyes — project guide, layout, design system, commands and publishing a release.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).