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/quan0715/open-press/claude-mdgit clone --depth 1 https://github.com/quan0715/open-pressWrote 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/quan0715/open-press/claude-md)<a href="https://agentmods.dev/instructions/quan0715/open-press/claude-md"><img src="https://agentmods.dev/badge/instructions/quan0715/open-press/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 | $0.02359 | $0.02359 |
| Opus 5 | $0.01179 | $0.01179 |
| Sonnet 5 | $0.00472 | $0.00472 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
open-press 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 5d 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 — 149 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.
Read AGENTS.md first — it owns the editable/non-editable path contract, commit prefixes, and engine philosophy. This file adds the architecture and command detail that requires reading multiple files to reconstruct.
Repo identity
This is the open-press framework monorepo (pnpm workspaces + turbo), not a downstream OpenPress workspace. If you ever find memory/AGENTS.md at the root, you are in a downstream project instead — stop and read that file.
Published packages ship lockstep at one version (fixed in .changeset/config.json):
| Package | Role |
|---|---|
@open-press/core |
Engine (engine/, plain .mjs) + React runtime (src/openpress/, TSX). Not bundled — consumers import source through the shipped vite.config.ts. |
@open-press/cli |
open-press binary, built with tsup. Thin wrapper over core's engine. |
@open-press/create |
npm create @open-press scaffolder. Slide workspaces only by design. |
apps/web |
Astro landing site (open-press.dev). Not published. |
press/ is the tracked dogfood workspace (financial-report, resume, school-report, slide, thesis, userstory). It is real committed source used to validate the pipeline — despite what AGENTS.md and .gitignore comments claim about it being ignored.
Commands
Node 24 is pinned in CI and .node-version (Trusted Publishing OIDC needs npm ≥ 11.5.1). Engine runtime contract is Node ≥ 20.
pnpm install
pnpm run typecheck # turbo → tsc per package
pnpm test # repo policy tests + turbo test
pnpm run build # turbo build (validates + renders every Press)
In this repo the open-press binary is not built locally — always invoke the engine directly:
node packages/core/engine/cli.mjs <command> .
Dogfood pipeline:
pnpm run dev:workspace # workbench at http://127.0.0.1:5173/workspace
pnpm run dev:web # Astro landing site
pnpm run openpress:pdf
pnpm run openpress:word
pnpm run openpress:deploy:dry-run
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.
- 5d ago First seen · 149 lines · 2,359 tokens per session scan A 0557eec5b76f
open-press CLAUDE.md is an instructions file published in the GitHub repository quan0715/open-press (14 stars, last pushed 7d ago), licensed MIT. It adds 2,359 tokens to every session, about $0.0118 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
starwind-ui AGENTS.md
AGENTS.md instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
stardrive AGENTS.md
AGENTS.md instructions for peltmonger/stardrive, covering 🛑 critical: repository bootstrap directive 🛑, general information and guidelines for ai agents, analyze your high-level use case first, how the .ai guidance files relate and this is an astro project.
markdy-com copilot-instructions.md
Copilot instructions for HoangYell/markdy-com, a project described as: 🎬 Open-source animated architecture diagrams as code. Diagram-native DSL, 17 layout engines, Web Animations API, and MCP server for AI agents.
specification.website CLAUDE.md
Claude Code instructions for jdevalk/specification.website, covering what this project is, status discipline, changelog, cardinal rules for content and architecture quick reference.
saferskills CLAUDE.md
Claude Code instructions for OpenLatch/saferskills, covering claude.md — saferskills, quick start, backend, frontend and codegen.
site CLAUDE.md
Claude Code instructions for HagiCode-org/site: 此配置文件指向本仓库的 AGENTS.md，其中包含项目特定的 AI 助手配置。.