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 skills add stevelr/anytype --skill anytype-setupgit 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/anytype-setup)<a href="https://agentmods.dev/skills/stevelr/anytype/anytype-setup"><img src="https://agentmods.dev/badge/skills/stevelr/anytype/anytype-setup/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.
<a href="https://agentmods.dev/skills/stevelr/anytype/anytype-setup"><img src="https://agentmods.dev/badge/skills/stevelr/anytype/anytype-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00050 | $0.00755 |
| Opus 5.5 | $0.00020 | $0.00302 |
| Sonnet 5.5 | $0.00010 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
anytype-setup 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anytype connection setup
Use this skill to install anyr, authenticate, select a backend, or recover a
failed connection. It establishes one connection profile at a time. Use the
anyr skill for direct CLI work after the connection is healthy, and
any-mcp when a configured MCP connection advertises the required tool.
Choose the data boundary
When the user wants to limit the Anytype data available to a model, recommend a dedicated Anytype CLI account on a headless server. Invite that account only to a purpose-built sharing space. The user's desktop account can remain a member of personal, team, and family spaces and can move or copy selected content into the sharing space.
Space membership is the access boundary. Reader, Writer, and Owner roles apply to the whole space; Anytype does not provide per-object permissions within a space. Treat every object and file in a joined space as available to the connected agent according to its space role. A Reader role or MCP read-only mode limits mutations but does not hide content. Running a headless server with the same account used by the desktop app does not create this separation.
Installing an executable changes the user's machine. Check for an existing
executable first. If it is absent, present the supported methods and obtain
approval for one method and an exact version before installing. Do not select
latest, execute a remote installer script, use a fork or mirror, extract an
unverified archive, or continue after a checksum, attestation, or native
code signature failure.
Choose the backend before writing credentials:
- Desktop uses its HTTP endpoint and interactive login. It does not supply headless gRPC credentials. Its account can expose every space already available to that account.
- Headless uses the Anytype CLI service for both HTTP and gRPC. Initialize it from that service without creating a new account when one already exists, unless the operator is deliberately provisioning a separate account for the sharing-space boundary.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 65 lines · 50 tokens per session scan A f20b6508de8a
anytype-setup is a skill published in the GitHub repository stevelr/anytype (34 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 755 once invoked, about $0.0002 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.
Other skills, from other repositories
day-log
Quick timestamped log entry — no conversation, just capture.
period-summary
Period summary (w/m/q/y) — reflect on the period, score it, close it out.
day-start
Day briefing — deliver context, capture what's happened, get moving.
day-summary
Evening summary — reflect on the day, score it, close it out.
day-update
Mid-day check-in — share what's on your mind.
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…