What is pip-web CLAUDE.md?

Project-specific instructions for Pip, a single-player Texas Hold'em poker web app played with play money and no account. They describe the project's documentation, code layers, conventions, and development workflow.

Use them when working on Pip's poker engine, game state, interface, copy, venue artwork, offline behavior, testing, or deployment.

They help an agent change the app without putting poker rules, game flow, saved data, and visual presentation in the wrong parts of the codebase.

pip-web CLAUDE.md — Instructions file for coding agents by playpip: Project-specific instructions for Pip, a single-player Texas Hold'em pok

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/playpip/pip-web/claude-md

Clone the repo

git clone --depth 1 https://github.com/playpip/pip-web

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/instructions/playpip/pip-web/claude-md.svg)](https://agentmods.dev/instructions/playpip/pip-web/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/playpip/pip-web/claude-md"><img src="https://agentmods.dev/badge/instructions/playpip/pip-web/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 912 This file is loaded in full into every session.

When invoked 912 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.

Model	Per session	Once invoked
Fable 5	$0.00912	$0.00912
Opus 5	$0.00456	$0.00456
Sonnet 5	$0.00182	$0.00182
Haiku 4.5	$0.00091	$0.00091

Measured 4d ago against content hash 8bc957723174, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pip-web 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 4d 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — agent guide for Pip

Pip is a clean, single-player Texas Hold'em web app (play money, no account needed, desktop-first). GitHub repo: playpip/pip-web.

Full documentation lives in docs/ — read it before non-trivial work. This file is the quick-start and the non-negotiables.

Read first (by task)

Doing…	Read
Anything	docs/README.md, docs/architecture.md
Poker rules / AI	docs/poker-engine.md
Tournament pacing / economy	docs/game-flow.md
UI / styling	docs/design.md
Copy / naming / tone	docs/brand.md
Venues / venue art	docs/venues.md
Persistence / backup / offline PWA	docs/data-and-offline.md
Setup / testing / conventions / deploy	docs/development.md

The three layers (respect the boundaries)

Engine — src/lib/poker/. Pure, deterministic, React-free, unit-tested. Rules live here.
Orchestration — src/store/game.ts (turn pacing, AI timers, economy) + src/store/profile.ts (persisted).
Presentation — src/components/, src/app/. Reads stores; look & feel only.

Rules change → engine (+ tests). Pacing/money → game store. Looks → components + tokens.

Non-negotiables

Package manager: pnpm. Never hand-pin versions — install latest, let pnpm resolve.
Tests: AVA, not Vitest. Engine changes ship with tests.
Colours: theme tokens only. Never hardcode bg-white/…, text-black, etc. Use foreground/<alpha> for subtle surfaces, bg-primary/text-primary-foreground for emphasis. Must work in both light and dark. (See docs/design.md.)
No real money framing. Play-money "chips" only; never show $. No casino textures, no pop-ups, no dark patterns. (See docs/brand.md.)
Determinism in the engine. Pass a seeded Rng; no Date.now()/Math.random() in logic that must be reproducible.
Engine stays pure. No React/store/browser imports in src/lib/poker/.
Persisted profile changes → bump PERSIST_VERSION + add a migrate branch in src/store/profile.ts.
set-state-in-effect (React 19 rule, enforced by convention) — use the patterns in docs/development.md (useHydrated, mount-form-while-open), not setState in useEffect.
Releases are automatic. Pushing to main deploys and cuts a release: the version auto-bumps (patch by default; #minor/#major in the commit subject line to bump harder — the body is ignored), tags, and publishes a GitHub Release. Don't bump package.json version by hand. (See docs/development.md → Deploy & releases.)

Read the full file on GitHub · 63 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.

4d ago First seen · 63 lines · 912 tokens per session scan A 8bc957723174

Subscribe to this mod's changes

pip-web CLAUDE.md is an instructions file published in the GitHub repository playpip/pip-web (10 stars, last pushed yesterday), licensed MIT. It adds 912 tokens to every session, about $0.0046 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.

Planning Web3 and blockchain card-game nextjs play-money poker single-player

pip-web CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md — agent guide for Pip

Read first (by task)

The three layers (respect the boundaries)

Non-negotiables

What this file has done since we first saw it

Other instructions, from other repositories

onchainai copilot-instructions.md

Hackathon-Stellaroid_Earn AGENTS.md

swarmfi CLAUDE.md

onchainai CLAUDE.md

quantum-shield AGENTS.md

evmole AGENTS.md