agentmods.dev

open-press AGENTS.md

open-press AGENTS.md is an instructions file for Codex, OpenCode from quan0715/open-press. It costs 1,183 tokens per session, scanned A, original, MIT.

Repository-specific instructions for contributing to the open-press framework, a project that includes a core engine, command-line scaffolder, skills, documentation, and a sample workspace.

In plain words
What is it for?
Use them when modifying open-press framework code, its command-line tools, bundled skills, website, documentation workspace, or tests.
Why use it?
They tell coding agents which areas they may edit, how downstream projects differ, and which contribution and commit rules apply.

Instructions file for CodexOpenCode

not rated 14 5d ago A scan 1,183 tokens original MIT
View the source file quan0715/open-press
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/quan0715/open-press/agents-md
Clone the repo
git clone --depth 1 https://github.com/quan0715/open-press

Made for: Codex, OpenCode.

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.

agentmods badge for open-press AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/quan0715/open-press/agents-md.svg)](https://agentmods.dev/instructions/quan0715/open-press/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/quan0715/open-press/agents-md"><img src="https://agentmods.dev/badge/instructions/quan0715/open-press/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,183 This file is loaded in full into every session.
When invoked 1,183 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.

ModelPer sessionOnce invoked
Fable 5 $0.01183 $0.01183
Opus 5 $0.00592 $0.00592
Sonnet 5 $0.00237 $0.00237
Haiku 4.5 $0.00118 $0.00118

Measured 4d ago against content hash f9ae86b47f3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

open-press 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 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.

AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

open-press framework — agent contract

This repo is the open-press framework: core engine/workbench packages, CLI scaffolder, bundled skills, docs, landing site, and a tracked dogfood workspace.

You are an agent contributing to open-press itself. Framework code lives under packages/apps/skills; the root press/ is the public dogfood workspace used to verify the framework with real output.

If you find memory/AGENTS.md at the workspace root, you're in a downstream workspace (an open-press project, not the framework repo itself). Read memory/AGENTS.md first for project-specific context. Downstream workspaces consume @open-press/core from npm; document work should normally stay in press/, openpress/settings.json, and local skills.

What you may edit

  • packages/core/ — runtime primitives, engine, render pipeline, workbench source, tests.
  • packages/cli/ — scaffolder and template sync code.
  • apps/web/ — landing site.
  • skills/ — independent agent skills. Some skills include starter/ files that agents can read, copy, and adapt.
  • press/ — tracked dogfood workspace. Hosts press/userstory/ (the OpenPress User Story Book) plus minimal social and slide Press for multi-Press verification. Use it to validate real content, style, PDF, deploy, and gallery routing.
  • docs/ — user-facing docs, migration notes, active specs, and implementation plans.
  • Root config: vite.config.ts / tsconfig.json / index.html / package.json / openpress/settings.json / README.md / .gitignore.

What you may not edit

  • packages/core/document/ — legacy local scratch path. Do not recreate it; root press/ is the dogfood workspace.
  • node_modules/, public/openpress/, dist-react/, .deploy/, .openpress/, .turbo/cache/ — generated/cache output. The only writable exception is the ephemeral .openpress/review/current.json handoff owned by openpress-collaborate; replace or remove it, never treat it as authored delivery source.

Read the full file on GitHub · 72 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.

  1. 4d ago First seen · 72 lines · 1,183 tokens per session scan A f9ae86b47f3b

Subscribe to this mod's changes

open-press AGENTS.md is an instructions file published in the GitHub repository quan0715/open-press (14 stars, last pushed 5d ago), licensed MIT. It adds 1,183 tokens to every session, about $0.0059 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.

a4agent-skillsai-agentsai-firstastroclaude-code
Related

Other instructions, from other repositories

stardrive 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.

peltmonger/stardrive · 2,707 tokens

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.

HoangYell/markdy-com · 426 tokens

saferskills CLAUDE.md

Claude Code instructions for OpenLatch/saferskills, covering claude.md — saferskills, quick start, backend, frontend and codegen.

OpenLatch/saferskills · 2,592 tokens

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.

jdevalk/specification.website · 7,526 tokens

ai-first-toolkit AGENTS.md

Instructions for techwolf-ai/ai-first-toolkit, covering techwolf ai-first toolkit, repository purpose, working conventions and codex install notes.

techwolf-ai/ai-first-toolkit · 649 tokens

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。.

HagiCode-org/site · 40 tokens