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/playpip/pip-web/agents-mdgit clone --depth 1 https://github.com/playpip/pip-webWhat 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 | $0.00558 | $0.00558 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
pip-web AGENTS.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 3d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repo (Pip — a clean single-player Texas
Hold'em web app). This mirrors CLAUDE.md; full docs are in
docs/. Read the relevant doc before non-trivial work.
Orientation
- What it is: play-money, local-first, desktop-first Hold'em vs AI. No account needed;
there is an optional one for cross-device sync only. GitHub repo:
playpip/pip-web. - Three layers (don't cross the boundaries):
src/lib/poker/— pure, deterministic, unit-tested engine (the rules).src/store/—game.ts(pacing/AI/economy),profile.ts(persisted).src/components/,src/app/— presentation only.
Where to read
- Overview & layout → docs/architecture.md
- Poker rules / AI → docs/poker-engine.md
- Tournament flow / economy → docs/game-flow.md
- Design system & tokens → docs/design.md
- Brand / voice → docs/brand.md
- Venues & venue art → docs/venues.md
- Setup, testing, conventions → docs/development.md
Non-negotiables
- pnpm for everything; never hand-pin versions.
- AVA for tests (not Vitest); engine changes ship with tests.
- Theme tokens only for colour (
foreground/<alpha>,bg-primary) — must work in light and dark. Never hardcodewhite/black. - No real-money framing: "chips", never
$; no casino textures or pop-ups. - Engine is pure & deterministic (seeded
Rng; no React/store imports). - Persisted-schema changes bump
PERSIST_VERSION+ add a migration. - Obey the
set-state-in-effectrule — by convention (see docs/development.md).
Definition of done
pnpm test:all passes — format, types, lint (biome), AVA, knip, audit — (plus
pnpm build for structural changes). Verify UI by running pnpm dev. Commit/push only when asked.
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.
- 3d ago First seen · 42 lines · 558 tokens per session scan A 8869429c90b5
pip-web AGENTS.md is an instructions file published in the GitHub repository playpip/pip-web (10 stars, last pushed 3d ago), licensed MIT. It adds 558 tokens to every session, about $0.0028 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
data-table-filters CLAUDE.md
Instructions for openstatusHQ/data-table-filters, covering claude.md, project overview, monorepo structure (pnpm + turborepo), key commands and database.
www-sacred AGENTS.md
Instructions for internet-development/www-sacred, covering agents.md, what this repo is, repo map, conventions and the fonts menu previews.
karakeep CLAUDE.md
Claude Code instructions for karakeep-app/karakeep, a project described as: A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search.
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.
agentgram CLAUDE.md
Instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.