A command-line skill for starting, attaching to, and checking the ARC daemon, which is the background service that makes ARC resources available. It helps agents use an existing service without disrupting it.

Use it to inspect service status, start a daemon when needed, or attach to a named instance. It is for managing the local ARC runtime.

It reduces mistakes such as starting conflicting service instances or stopping a service another session is using. It also provides a status-first workflow before changes are made.

daemon — Skill for Claude Code by ArcBlock/agent-skills

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.

Any agent

npx skills add ArcBlock/agent-skills --skill daemon

Clone the repo

git clone --depth 1 https://github.com/ArcBlock/agent-skills

Made for: Claude Code.

Or install arc, the plugin that ships this one along with the rest of its 7 skills, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/arcblock/agent-skills/daemon/github.svg)](https://agentmods.dev/skills/arcblock/agent-skills/daemon)

Your own site

<a href="https://agentmods.dev/skills/arcblock/agent-skills/daemon"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/daemon/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/arcblock/agent-skills/daemon"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/daemon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,524 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.01524
Opus 5.5	$0.00008	$0.00610
Sonnet 5.5	$0.00004	$0.00305
Haiku 4.5	$0.00002	$0.00152

Measured 1mo ago against content hash 2f724d6e62cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

daemon 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.

plugins/arc/skills/daemon/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARC skill: daemon

Bootstrap a running ARC daemon so L1 paths (mounts, blocklets, MCP, UI/WM) become real.

Prefer

Discover this catalog first: arc skill or arc skill list
Load only the booklet you need: arc skill show <name>
Prefer JSON for agents: arc skill list --json (or global --json when supported)

Safe rules

Prefer inspecting status before mutating: arc service status.
Do not kill or force-stop a daemon you did not start unless the human explicitly asked.
Never stop purpose=observe daemons. Session end is not a stop. Killing observe is a contract break — the row stays in /dev/instances as DOWN, it does not disappear.
Prefer attaching to an already-running daemon over spawning a second conflicting instance on the same --home/port.
Discovery commands must be side-effect free. Do not probe by starting long-lived servers "just to see help".
Optional isolation: arc service start --instance <name> --home <dir> (see arc service start --help).

Typical flow

arc --help
arc skill list
arc service status

# Start when needed (check --help for flags)
arc service start
# or: arc service start --instance <name> --port <port>   (named instance)

arc service status
# Then L1 — targets the instance you just started:
arc afs ls /
arc afs explain /
arc afs read /.knowledge

Started a named instance (arc service start --instance <name>) instead of the default one? arc afs never guesses which world you mean — add --instance <name> to every arc afs call in this booklet (bare arc afs targets the default instance and fails closed, non-zero exit, if that one has no daemon running). arc skill show afs covers this in depth.

arc service start registers this daemon in the machine instance catalog ($ARC_INSTANCES_DIR, default ~/.arc/instances). Clean arc service stop removes the row. Crash leftovers stay until GC.

Headless Linux / no D-Bus session? Read Headless vault below before arc service start — do not invent a vault key.

Read the full file on GitHub · 120 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.

1mo ago First seen · 120 lines · 19 tokens per session scan A 2f724d6e62cf

Subscribe to this mod's changes

daemon is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 19 tokens to every session and 1,524 once invoked, about $0.0001 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 2026-09-14.

DevOps and cloud

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.