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 skills/stevelr/anytype/anyrnpx skills add stevelr/anytype --skill anyrgit clone --depth 1 https://github.com/stevelr/anytypeWrote 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/skills/stevelr/anytype/anyr)<a href="https://agentmods.dev/skills/stevelr/anytype/anyr"><img src="https://agentmods.dev/badge/skills/stevelr/anytype/anyr.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 | $0.00046 | $0.02888 |
| Opus 5 | $0.00023 | $0.01444 |
| Sonnet 5 | $0.00009 | $0.00578 |
| Haiku 4.5 | $0.00005 | $0.00289 |
Grade A, and why
anyr 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.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anytype CLI (anyr)
anyr lists, searches, and manipulates Anytype objects through the local
Anytype HTTP and gRPC APIs. Common object, schema, search, collection, Markdown,
and byte-transfer operations use REST. Rich file discovery, typed body blocks,
archived-object cleanup, space administration, backup/restore, and some chat
operations require gRPC. The complete CLI documentation is available in the
Anytype Toolbox repository.
Tool choice: Use this skill for explicit CLI workflows, unavailable MCP
tools, and documented CLI-only fallbacks. Use anytype-setup to install
anyr, authenticate, select or change endpoints, or recover a backend. When
connected any-mcp tools advertise the required capability, use the any-mcp
skill instead.
Prerequisites
The anyr executable must be on PATH, and a reachable Anytype desktop or
headless service must have valid endpoint-specific credentials. The examples
use jq for JSON processing. OpenSSL is optional and appears only in the
encrypted file-keystore example.
The configured Anytype account determines the accessible spaces, including
the scope of a global search. When the user wants to limit model-visible data,
use anytype-setup to configure a dedicated headless account invited only to
a purpose-built sharing space. Anytype space roles do not provide per-object
isolation within that space.
Mental model
- Everything lives in a space. Commands take a space name or id
(
"Work"orbafy...) interchangeably. - A "document" is an object: it has a
type(page, task, note, bookmark, ...), aname, typedproperties, and a markdownbody. - Object content round-trips as markdown:
object getreturns it,object create/updateaccept--body/--body-file. - Type keys, property keys, and tag names are per-space. Discover them with
anyr type list SPACE,anyr property list SPACE,anyr tag list .... - Object
getandsearchresults with--jsoninclude properties.
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.
- 4d ago First seen · 248 lines · 46 tokens per session scan A f0f2042fd22d
anyr is a skill published in the GitHub repository stevelr/anytype (32 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,888 once invoked, about $0.0002 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 skills, from other repositories
documentation-server
Use when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval. Also use when interacting with the documentation server web interface, managing uploads, or performing AI-powered document analysis. Use this instead of MCP-native…
linkly-ai
Search, browse, read, and take notes across the user's documents indexed by Linkly AI — local files and linked cloud libraries. Use when the user asks to 'search my documents', 'find files about a topic', 'read a local document', 'what's in this folder', 'list the files in that library', 'browse document outlines'…
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
vault
Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.
okfshare
Use when a user wants to discover, validate, publish, update, retrieve, search, cite, inspect, or roll back Open Knowledge Format bundles, or wants to safely share project knowledge with a specified audience. This is a skills-only workflow and does not authenticate the CLI.
synorive
检索用户本机的内容库 —— 文档、代码、图片里的文字、网页存档、视频台词，都能用中文语义搜。当用户提到"我之前存过""找一下我的""那个文件在哪""我记得看过"这类需要翻自己资料的请求时用它。也能把新文件加入索引、找相似内容、按时间看分布、看实体关系图。不要用于搜索公开网络信息（那是 WebSearch 的活）。.