scrapai-cli AGENTS.md

A short pointer file telling AI coding assistants that CLAUDE.md contains all project rules. It deliberately keeps no separate rules so the instructions do not drift apart.

In plain words
What is it for?
Use it as an entry point that directs Cursor, Windsurf, Codex, Gemini, or other assistants to read CLAUDE.md before working on the project.
Why use it?
It prevents assistants from following outdated or conflicting guidance in multiple files. They have one stated source of truth for the project's rules.

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/discourselab/scrapai-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/discourselab/scrapai-cli

Made for: Codex, OpenCode.

Per session 135 This file is loaded in full into every session.
When invoked 135 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 $0.00135 $0.00135
Opus 5 $0.00068 $0.00068
Sonnet 5 $0.00027 $0.00027
Haiku 4.5 $0.00014 $0.00014

Measured 3d ago against content hash addcdc9623b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scrapai-cli 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.

AGENTS.md · 6 lines

What it actually says

scrapai CLI — Agent Rules (Cursor / Windsurf / Codex / Gemini / other agents)

All agent instructions live in CLAUDE.md. Read that file — it is the single source of truth for every AI assistant.

This file intentionally contains no rules of its own. Duplicating instructions here only causes drift: this file previously said "process one website at a time, sequential only, never parallel," which directly contradicted CLAUDE.md (it supports up to 5 in parallel). To prevent that, keep AGENTS.md a thin pointer and never add a rule, command, or principle here.

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 · 6 lines · 135 tokens per session scan A addcdc9623b4

Subscribe to this mod's changes

scrapai-cli AGENTS.md is an instructions file published in the GitHub repository discourselab/scrapai-cli (115 stars, last pushed 7d ago), licensed Apache-2.0. It adds 135 tokens to every session, about $0.0007 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.