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/plmbr/nui/claude-mdgit clone --depth 1 https://github.com/plmbr/nuiWhat 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 | $0.02763 | $0.02763 |
| Opus 5 | $0.01381 | $0.01381 |
| Sonnet 5 | $0.00553 | $0.00553 |
| Haiku 4.5 | $0.00276 | $0.00276 |
Grade A, and why
nui 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 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Backend (Go)
go build ./... # compile
go test . ./cmd/... ./internal/... # run tests (avoids ui/node_modules)
./scripts/test-all.sh # Go + Vitest + Playwright E2E
go run . server # build + run server on :8080
go run . server --port 3000 # custom port (use this for development)
go run . server -a claude-code -m "Review README" -w . --open --hide-input
Frontend (run from ui/)
npm install
npm run dev # Vite dev server with HMR (proxies /api to Go server)
npm run build # compile to ui/dist (required before go build)
npm run lint # ESLint
Full production build
cd ui && npm run build && cd .. && go build -o nui_bin . && ./nui_bin server
ui/distmust exist beforego build— it is embedded into the binary at compile time viaui/embed.go(//go:embed all:dist).
Docker images (run from docker/)
docker build -f claude-code/Dockerfile -t nui-claude-code:latest .
docker build -f pi/Dockerfile -t nui-pi:latest .
docker build -f codex/Dockerfile -t nui-codex:latest .
docker build -f opencode/Dockerfile -t nui-opencode:latest .
All docker sandbox images listen on port 8090 and share http_nui_agent.py. They forward ANTHROPIC_API_KEY, ANTHROPIC_BASE_URL, OPENAI_API_KEY, and OPENAI_BASE_URL from the host. nui adds --add-host=<hostname>:host-gateway when a base URL resolves to loopback.
Architecture
Request flow
flowchart LR
Browser -->|REST| API["/api/*"]
Browser -->|AG-UI SSE| AGUI["/api/sessions/:id/ag-ui"]
API --> Store["~/.nui/data.json"]
AGUI --> ADLAgent
ADLAgent --> Manager
Manager --> Harnesses["ClaudeCode / Pi / Codex / OpenCode"]
Manager --> HTTPExt["HTTPExtensionAgent"]
HTTPExt --> DockerRemote["Docker / Remote"]
In development, Vite (:5173) proxies /api to the Go server.
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 · 200 lines · 2,763 tokens per session scan A 4fffbe1ec465
nui CLAUDE.md is an instructions file published in the GitHub repository plmbr/nui (5 stars, last pushed 6d ago), licensed MIT. It adds 2,763 tokens to every session, about $0.0138 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 2026-08-31.
Other instructions, from other repositories
pi-agent-dashboard AGENTS.md
Instructions for BlackBeltTechnology/pi-agent-dashboard, covering pi dashboard, docs-first gate — kb before grep (per-turn doctrine), code instructions (per-turn doctrine), investigation protocol — index first and documentation update protocol.
rn-dev-agent AGENTS.md
Instructions for Lykhoyda/rn-dev-agent, covering repository guide for agents, repository map, editing rules, architecture rules and supported node runtimes.
pi-agent-dashboard CLAUDE.md
Instructions for BlackBeltTechnology/pi-agent-dashboard, a project described as: Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote control via mDNS or zrok tunnel. Coexists with pi's TUI — doesn't…
kungfu CLAUDE.md
Claude Code instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
agents-universe CLAUDE.md
Instructions for agents-universe/agents-universe, covering agents universe — enterprise ai agent framework, project overview, monorepo layout, development commands and api (from packages/api/).