anytype-agents-skill: Instructions file for Codex

AGENTS.md

anytype-agents-skill AGENTS.md is an instructions file for Codex, OpenCode from anyproto/anytype-agents-skill. It costs 2,302 tokens per session, scanned A, original, MIT.

Instructions for using Anytype Agent Runtime, a Go-based tool that runs JavaScript against Anytype, a local-first app for notes, tasks, bookmarks, and structured knowledge.

In plain words
What is it for?
It helps set up the runtime from a release or source code and use the Anytype API to manage objects, types, collections, tags, and searches.
Why use it?
It explains what Anytype stores and how to prepare the runtime before running scripts that interact with it.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is anyproto/anytype-agents-skill's own configuration. It tells Codex and OpenCode how to work on anytype-agents-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything anytype-agents-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to anyproto/anytype-agents-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/anyproto/anytype-agents-skill/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/anyproto/anytype-agents-skill

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 anytype-agents-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anyproto/anytype-agents-skill/agents-md/github.svg)](https://agentmods.dev/instructions/anyproto/anytype-agents-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/anyproto/anytype-agents-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/anyproto/anytype-agents-skill/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for anytype-agents-skill AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/anyproto/anytype-agents-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/anyproto/anytype-agents-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,302 This file is loaded in full into every session.
When invoked 2,302 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02302 $0.02302
Opus 5.5 $0.00921 $0.00921
Sonnet 5.5 $0.00460 $0.00460
Haiku 4.5 $0.00230 $0.00230

Measured 2mo ago against content hash 0caf2b03e270, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

anytype-agents-skill 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 2mo 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 · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anytype Agent Runtime

What is Anytype

Anytype is a local-first, privacy-focused knowledge management platform. Everything in Anytype is an object with a type. Types define which properties an object can have. You can:

  • Create and manage objects (pages, notes, tasks, bookmarks, custom types)
  • Organize with types (define schemas with properties), collections (curated lists), and tags
  • Search across objects using full-text and semantic vector search
  • Build structured knowledge bases with typed properties (text, number, date, select, multi_select, checkbox, etc.)
  • Properties are global — a property key has one format across the entire space

This project uses the Anytype Agent Runtime (a Go-based JS engine) to execute JavaScript that interacts with the Anytype API through the anytypeHelper library.

Setup

Before running scripts, check that anytype-agent-runtime is installed:

which anytype-agent-runtime

If not found, install it yourself: don't ask user to do it. If you are not sure about path -- just download the binary to the current folder and run it.

# Option 0: from github releases:
# check https://github.com/anyproto/anytype-agent-runtime/releases, download binary for current OS and install to PATH.

# Option 1: from source (requires Go)
git clone https://github.com/anyproto/anytype-agent-runtime.git /tmp/anytype-agent-runtime
cd /tmp/anytype-agent-runtime && go install . && cd -

# Option 2: if the repo is already cloned locally
cd /path/to/anytype-agent-runtime && go install . && cd -

After install, verify: anytype-agent-runtime --help

It also worth checking github/releases to make sure that newest version is installed.

How to run JS

Write a .js file that exports a main() function, then execute it. The -m . flag makes the current directory a module search path, so anytypeHelper.js in this folder is available as import { createClient } from "anytypeHelper@v1".

anytype-agent-runtime -m . my-script.js

Read the full file on GitHub · 210 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. 2mo ago First seen · 210 lines · 2,302 tokens per session scan A 0caf2b03e270

Subscribe to this mod's changes

anytype-agents-skill AGENTS.md is an instructions file published in the GitHub repository anyproto/anytype-agents-skill (77 stars, last pushed 6mo ago), licensed MIT. It adds 2,302 tokens to every session, about $0.0092 per session on Opus 5.5. 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.

Related

anytype-agents-skill AGENTS.md compared with instructions from other repositories

anytype-agents-skill AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
anytype-agents-skill AGENTS.mdanyproto/anytype-agents-skillInstructions file776mo agoMITA2,302Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode