New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Mycelium Remote Agent

by mycelium-io in mycelium-io/mycelium

Bootstrap yourself as an ephemeral Mycelium agent when your environment is wired to a hub.

Custom licenceAuto-check: notes

Install Mycelium Remote Agent

skills CLI
$ npx skills add mycelium-io/mycelium --skill mycelium-remote-agent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mycelium-io/mycelium mycelium-remote-agent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mycelium-io/mycelium.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/mycelium-remote-agent .claude/skills/mycelium-remote-agent && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mycelium-remote-agent
GitHub stars
119
Token cost
~3k tokens
SKILL.md length
1,317 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Custom licence

At a glance

Bootstrap yourself as an ephemeral Mycelium agent when your environment is wired to a hub.

  • Works in 6 steps: Make sure the CLI is installed → Claim your identity → Read the room. Do not write to it. → …
  • SKILL.md covers What the environment already…, 1. Make sure the CLI is…, 2. Claim your identity and 3. Read the room. Do not write…, plus 5 more sections
  • Calls curl, sh and uv; reaches astral.sh; needs MYCELIUM_AGENT_AUTH_CLIENT_SECRET

What it does

Mycelium Remote Agent is an agent skill from mycelium-io/mycelium. Bootstrap yourself as an ephemeral Mycelium agent when your environment is wired to a hub. Claims a distinct per-session identity (delegated from a shared workload credential, owned by the human), picks up or opens a task on the room's board, and reports progress there. Use at the start of a remote or cloud session (Claude Code cloud, a CI job) whose environment sets MYCELIUMAPIURL and MYCELIUMAGENTAUTHCLIENTID, or when asked to "report to mycelium", "join the room", "take something off the board", or "post…

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Multi-agent coordination + persistent memory, semantic negotiation, async rooms, and a shared knowledge graph.

Example prompts

  • “report to mycelium”
  • “join the room”
  • “take something off the board”
  • “/mycelium-remote-agent”

Requirements

  • Python 3
  • A credential in MYCELIUM_AGENT_AUTH_CLIENT_SECRET

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Make sure the CLI is installed
  2. Claim your identity
  3. Read the room. Do not write to it.
  4. Work a task, not a room
  5. Report at milestones — in the row
  6. Close the task out before you exit

What it can do on your machine

Read from SKILL.md and the folder at commit 6a814e1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • sh
    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • astral.sh

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MYCELIUM_AGENT_AUTH_CLIENT_SECRET

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mycelium Remote Agent loads about 3k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 1,317 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~140
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePipes a well-known installer script into a shellSKILL.md:34
    command -v uv >/dev/null 2>&1 || curl -fsSL https://astral.sh/uv/install.sh | sh

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,317 words (~2,978 tokens).

“You are running in an environment wired to a Mycelium hub: a shared coordination room on a remote server. This skill gives you a distinct identity in that room, tells you how to work a task of that room's board…”

— opening of SKILL.md by mycelium-io, Custom licence
name
mycelium-remote-agent
user_invocable
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/mycelium-remote-agent of mycelium-io/mycelium.

Open the folder on GitHubat commit 6a814e1

Compare with similar skills

Mycelium Remote Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Mycelium Remote Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mycelium Remote Agent this skillmycelium-io/mycelium119—~3kAutomated safety check: NotesCustom licence
Remotion Interactivityremotion-dev/remotion63k5 repos~4.8kAutomated safety check: PassCustom licence
Remotiondavila7/claude-code-templates33k1 repos~1.6kAutomated safety check: PassMIT
Remotionnexu-io/open-design100k—~301Automated safety check: PassApache-2.0
Remotion Captionsremotion-dev/remotion63k5 repos~294Automated safety check: PassCustom licence
Remotion Markupremotion-dev/remotion63k2 repos~4.6kAutomated safety check: PassCustom licence

Similar skills

  • Remotion Interactivity

    remotion-dev/remotion

    Official

    Structure Remotion markup for interactivity. An agent skill from remotion-dev/remotion.

    63k GitHub starsUsed in 5 repos~4.8k tokens
    Media & CreativeAuto-check passed

  • Remotion

    davila7/claude-code-templates

    Best practices and comprehensive guide for Remotion - programmatic video creation in React with animations, compositions, and media handling

    33k GitHub starsUsed in 1 repo~1.6k tokens
    Media & CreativeAuto-check passed

  • Remotion

    nexu-io/open-design

    Programmatic video creation with React. An agent skill from nexu-io/open-design.

    100k GitHub stars~301 tokensUpdated today
    Media & CreativeAuto-check passed

  • Remotion Captions

    remotion-dev/remotion

    Official

    Transcribing, displaying and animating captions. An agent skill from remotion-dev/remotion.

    63k GitHub starsUsed in 5 repos~294 tokens
    Media & CreativeAuto-check passed

  • Remotion Markup

    remotion-dev/remotion

    Official

    Content, animation and effects best practices. An agent skill from remotion-dev/remotion.

    63k GitHub starsUsed in 2 repos~4.6k tokens
    Media & CreativeAuto-check passed

  • Bootstrap Soul

    bytedance/deer-flow

    Runs a short adaptive conversation with you and writes a personalized SOUL.md that defines your AI partner's name, personality, communication style and boundaries.

    84k GitHub starsUsed in 2 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

More from mycelium-io/mycelium

  • Audit Comments

    mycelium-io/mycelium

    Cheap-model audit of comments and inline docs for temporal/historical narration, overly long prose, over-referencing of GitHub issues / PR numbers / plan-step IDs, and design-justification /…

    119 GitHub stars~3.1k tokensUpdated today
    Auto-check passed

  • Modern Python

    mycelium-io/mycelium

    Modern Python tooling practices for the mycelium project. An agent skill from mycelium-io/mycelium.

    119 GitHub stars~752 tokensUpdated today
    Auto-check passed

  • Screenshot

    mycelium-io/mycelium

    Take a screenshot of the running Mycelium app, or of CLI output rendered as a terminal card, or record a short video of a flow with a visible cursor and click/zoom animations.

    119 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Mycelium

    mycelium-io/mycelium

    Multi-agent coordination layer with persistent memory. An agent skill from mycelium-io/mycelium.

    119 GitHub stars~6.5k tokensUpdated today
    Auto-check passed

  • Precommit

    mycelium-io/mycelium

    Run precommit checks (lint, format, tests) on the mycelium codebase.

    119 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Generate CLI Docs

    mycelium-io/mycelium

    Regenerate the HTML docs site (CLI Reference, Configuration, content sections) from decorators, the pydantic config schema, and markdown source files

    119 GitHub stars~641 tokensUpdated today
    Auto-check passed

Questions about Mycelium Remote Agent

What does Mycelium Remote Agent do?

Bootstrap yourself as an ephemeral Mycelium agent when your environment is wired to a hub. Mycelium Remote Agent is an agent skill from mycelium-io/mycelium. Bootstrap yourself as an ephemeral Mycelium agent when your environment is wired to a hub.

How do I install Mycelium Remote Agent in Claude Code?

Run `npx skills add mycelium-io/mycelium --skill mycelium-remote-agent -a claude-code`. Or copy the skill folder (.claude/skills/mycelium-remote-agent in mycelium-io/mycelium) into .claude/skills/mycelium-remote-agent in your project. Claude Code loads it when a task matches its description.

How do I install Mycelium Remote Agent in Codex?

Run `npx skills add mycelium-io/mycelium --skill mycelium-remote-agent -a codex`. Or copy the skill folder (.claude/skills/mycelium-remote-agent in mycelium-io/mycelium) into .agents/skills/mycelium-remote-agent in your project. Codex loads it when a task matches its description.

Can I use Mycelium Remote Agent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mycelium-io/mycelium --skill mycelium-remote-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mycelium-remote-agent, .gemini/skills/mycelium-remote-agent, .github/skills/mycelium-remote-agent and .opencode/skills/mycelium-remote-agent in your project.

What does Mycelium Remote Agent need to run?

Going by SKILL.md and its folder, Mycelium Remote Agent needs the command-line tools its instructions call (curl, sh and uv) and credentials named MYCELIUM_AGENT_AUTH_CLIENT_SECRET. Our summary lists: Python 3; A credential in MYCELIUM_AGENT_AUTH_CLIENT_SECRET.

Does Mycelium Remote Agent access the network?

SKILL.md names 1 domain. In commands or code: astral.sh; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Mycelium Remote Agent safe to install?

Our automated static check of SKILL.md found notes only (pipes a well-known installer script into a shell), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Mycelium Remote Agent use?

Mycelium Remote Agent has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Mycelium Remote Agent use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mycelium Remote Agent?

Skills that share tags, products or a category with Mycelium Remote Agent: Remotion Interactivity (remotion-dev/remotion, 63k stars), Remotion (davila7/claude-code-templates, 33k stars), Remotion (nexu-io/open-design, 100k stars) and Remotion Captions (remotion-dev/remotion, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mycelium Remote Agent?

mycelium-io (a GitHub organization) maintains it in mycelium-io/mycelium, which has 119 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 10, 2026.

Source: mycelium-io/mycelium on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.