A set of instructions for embedding Pi, an AI agent, in a browser-based chat interface using web components. It covers the ChatPanel, browser storage, artifacts, and tools provided by the pi-web-ui package.

Use it to add a Pi chat panel to a web app, configure IndexedDB storage, connect model and agent components, or debug the web-ui setup and its tool renderers.

It reduces guesswork when connecting the browser interface to Pi's model and agent libraries and helps keep browser-specific code separate from command-line behaviour.

pi-web-ui — Skill for Claude Code by romiluz13/pi-agent-skills

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.

Any agent

npx skills add romiluz13/pi-agent-skills --skill pi-web-ui

Clone the repo

git clone --depth 1 https://github.com/romiluz13/pi-agent-skills

Made for: Claude Code.

Or install pi-skill, the plugin that ships this one along with the rest of its 11 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-web-ui/github.svg)](https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-web-ui)

Your own site

<a href="https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-web-ui"><img src="https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-web-ui/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-web-ui"><img src="https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-web-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 392 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00089	$0.00392
Opus 5.5	$0.00036	$0.00157
Sonnet 5.5	$0.00018	$0.00078
Haiku 4.5	$0.00009	$0.00039

Measured 2mo ago against content hash 994dcf5a1a47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pi-web-ui 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 2mo 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.

pi-skills/pi-web-ui/SKILL.md · 27 lines

What it actually says

Pi web UI (`@mariozechner/pi-web-ui`)

Grounding

pi-mono/packages/web-ui/README.md — features, installation, Quick Start snippet, APIs referenced there.
pi-mono/packages/web-ui/example/ — runnable minimal app (README.md, package.json, entry source).
Supporting libraries: pi-mono/packages/ai/README.md and pi-mono/packages/agent/README.md when wiring model + Agent as shown in web-ui README.

Invariants

README documents stack (mini-lit, Tailwind v4) and integration shape; do not substitute other component frameworks without explicit user request and README cross-check.

Workflows

Bootstrap: Follow README Quick Start imports (ChatPanel, storage stores, setAppStorage, defaultConvertToLlm) exactly as in pi-mono/packages/web-ui/README.md.
Compare to CLI: CLI behavior lives in pi-coding-agent; browser concerns stay in web-ui README — cite both paths when contrasting.

Anti-patterns

Do not invent artifact or tool names not listed in pi-mono/packages/web-ui/README.md without opening pi-mono/packages/web-ui/src/tools/ for the specific renderer.

Files

What ships with it

1 file 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.

references/CORPUS.md 244 B

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.

2mo ago First seen · 27 lines · 0 tokens per session scan A 994dcf5a1a47

Subscribe to this mod's changes

pi-web-ui is a skill published in the GitHub repository romiluz13/pi-agent-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 89 tokens to every session and 392 once invoked, about $0.0004 per session on Opus 5.5. 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.

Frontend

pi-web-ui next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pi-web-uiromiluz13/pi-agent-skills	Skill	20	7mo ago	MIT	A	89	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	3d ago	MIT	A	200	Claude Code, Codex
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	6d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code