pagecord AGENTS.md

pagecord AGENTS.md is an instructions file for Codex, OpenCode from lylo/pagecord. It costs 5,702 tokens per session, scanned A, original, no licence file.

Repository instructions for coding agents working on the Pagecord project. They describe project principles, how state changes should work, and code style.

In plain words
What is it for?
Use them when asking an agent to change Pagecord code, especially when the task affects application state, comments, or formatting.
Why use it?
They give the agent project-specific rules to follow instead of relying on generic coding assumptions.

Instructions file for CodexOpenCode

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/lylo/pagecord/agents-md
Clone the repo
git clone --depth 1 https://github.com/lylo/pagecord

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 pagecord AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lylo/pagecord/agents-md.svg)](https://agentmods.dev/instructions/lylo/pagecord/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lylo/pagecord/agents-md"><img src="https://agentmods.dev/badge/instructions/lylo/pagecord/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,702 This file is loaded in full into every session.
When invoked 5,702 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.05702 $0.05702
Opus 5 $0.02851 $0.02851
Sonnet 5 $0.01140 $0.01140
Haiku 4.5 $0.00570 $0.00570

Measured 3d ago against content hash e3f4a65a9c33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pagecord AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **A GET must be safe.** Never write state in response to a GET, not even to a cookie or the session. Turbo prefetches links on hover, so a `link_to` that writes a preference fires just by passing the cursor over it. Th
AGENTS.md · 242 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 3d ago First seen · 242 lines · 5,702 tokens per session scan A e3f4a65a9c33

Subscribe to this mod's changes

pagecord AGENTS.md is an instructions file published in the GitHub repository lylo/pagecord (188 stars, last pushed 5d ago), with no licence file. It adds 5,702 tokens to every session, about $0.0285 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.