Agent skill

Muninn Boot

by oaustegard in oaustegard/claude-skills

Puts oaustegard/muninn-utilities on the container Python path — runs scripts/boot.sh, which shallow-clones the repo (codeload tarball as fallback) and writes the .pth.

MITAuto-check passedProductivity & Automation

Install Muninn Boot

skills CLI
$ npx skills add oaustegard/claude-skills --skill muninn-boot -a claude-code

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

GitHub CLI
$ gh skill install oaustegard/claude-skills muninn-boot --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/oaustegard/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/muninn-boot .claude/skills/muninn-boot && 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
muninn-boot
GitHub stars
150
Token cost
~1.1k tokens
SKILL.md length
536 words
Files
3 (incl. scripts)
Skills in repo
66
Repo updated
First seen
Licence
MIT

At a glance

Puts oaustegard/muninn-utilities on the container Python path — runs scripts/boot.sh, which shallow-clones the repo (codeload tarball as fallback) and writes the .pth.

  • Works in 5 steps: Warm-path check: sentinel… → Source $MUNINN_PROJECT_DIR/GitHub.env… → git clone --depth 1… → …
  • The first message of any new Muninn conversation
  • SKILL.md covers MCP boot parts, boot.sh steps, GitHub.env in Cowork and Pinning
  • Runs Shell scripts from its folder; calls bash and git; needs GH_TOKEN

What it does

Muninn Boot is an agent skill from oaustegard/claude-skills. Puts oaustegard/muninn-utilities on the container Python path — runs scripts/boot.sh, which shallow-clones the repo (codeload tarball as fallback) and writes the .pth. The boot payload itself comes from the Muninn MCP connector: call its boot tool after this script. Trigger on the first message of any new Muninn conversation, or when the user says "boot up" / "boot" — unless the message contains "skip boot". Idempotent: a warm container exits in ~0s via a sentinel.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `CHANGELOG.md` and `scripts/boot.sh`).

It sits in Productivity & Automation, covering App automation through connectors. It works with Python and GitHub. The repository describes itself as: My collection of Claude skills. The licence is MIT.

When your agent uses it

  • The first message of any new Muninn conversation
  • The user says boot up / boot — unless the message contains skip boot

Example prompts

  • “boot up”
  • “— unless the message contains”
  • “/muninn-boot”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Warm-path check: sentinel /home/claude/.muninn-booted present and
  2. Source $MUNINN_PROJECT_DIR/GitHub.env (default /mnt/project) if present.
  3. git clone --depth 1 oaustegard/muninn-utilities at MUNINN_UTILS_REF
  4. Write muninn-remembering.pth at a site-packages directory resolved from
  5. Write the sentinel, print a four-line footer: transport and commit, pth

What it can do on your machine

Read from SKILL.md and the folder at commit cf49d47. 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

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

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

  • Credentials

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

    • GH_TOKEN

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

Context cost

Muninn Boot loads about 1.1k tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 536 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 passed

The automated check found no risky patterns in SKILL.md.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from oaustegard/claude-skills at commit cf49d47, republished under its MIT licence (© oaustegard). 536 words, ~1,111 tokens.

Download SKILL.mdSave it as .claude/skills/muninn-boot/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
muninn-boot
description
Puts oaustegard/muninn-utilities on the container Python path — runs scripts/boot.sh, which shallow-clones the repo (codeload tarball as fallback) and writes the .pth. The boot payload itself comes from the Muninn MCP connector: call its `boot` tool after this script. Trigger on the first message of any new Muninn conversation, or when the user says "boot up" / "boot" — unless the message contains "skip boot". Idempotent: a warm container exits in ~0s via a sentinel.
metadata.version
2.0.1
metadata.source
https://github.com/oaustegard/muninn-utilities/tree/main/muninn-boot

Muninn Boot

Two steps, in this order:

bash
bash "$(dirname "$(find / -name boot.sh -path '*muninn-boot*' 2>/dev/null | head -1)")/boot.sh"

then call the Muninn MCP boot tool. The script fetches code; the tool delivers identity, ops, recent memories and reminders. Memory reads and writes go through the connector's recall / remember / forget / muninn_config tools, so the container holds no Turso credential and this skill reads no Turso.env. Direction in memory ce3b8b75, the plan in 69f3301c.

Prior to 2.0.0 this skill sideloaded claude-skills and ran the Python boot() itself. Marketplace sync now places claude-skills in every session (/root/.claude/skills/synced/<id>/ in Cowork, /mnt/skills/user on Claude.ai), and the worker runs boot. "skinny boot" (BOOT_MODE=perch) has no effect until the worker's boot takes a mode.

MCP boot parts

The boot tool's payload is larger than the harness output cap, so it comes in parts. Call boot with no arguments; its footer says whether the payload is complete or names the next part (boot({part: 2}), then 3, and so on). Call every part the footer names before replying. The harness may persist a part to a file instead of showing it ("Output too large ... saved to ..."); read that file in full. A part that was persisted has already been delivered, so never call boot again with the same part to recover it.

boot.sh steps

Check metadata.version at the top of this file right before running. Below 2.0.0 the on-disk script is the old one that sideloads claude-skills and runs the Python boot() itself; marketplace sync can replace the copy mid-session, so a session may run 1.x once and 2.x next.

  1. Warm-path check: sentinel /home/claude/.muninn-booted present and /home/claude/muninn-utilities/muninn_utils exists → exit 0.
  2. Source $MUNINN_PROJECT_DIR/GitHub.env (default /mnt/project) if present. Transitional — it goes once GitHub write tools exist on the worker. The container presets GH_TOKEN=proxy-injected, a truthy placeholder; without the file, GitHub API calls from the container 401 and the script says so. Memory tools are unaffected.
  3. git clone --depth 1 oaustegard/muninn-utilities at MUNINN_UTILS_REF (default main; branch, tag or full SHA) → /home/claude/muninn-utilities. Measured 1.3s cold in Cowork. Fallback where the git proxy refuses github.com: the codeload tarball, which works on Claude.ai and is 403 in Cowork (there git works). If both fail the script exits 1.
  4. Write muninn-remembering.pth at a site-packages directory resolved from sys.path at runtime (/root/.local/lib/python3.11/site-packages in Cowork, measured 2026-09-19) listing the repo, remembering/, $HOME, and every skill scripts/ directory found under either skills root.
  5. Write the sentinel, print a four-line footer: transport and commit, pth path, and the reminder to call the MCP boot tool.
Show full SKILL.md (127 more words)Show less

GitHub.env in Cowork

Only GitHub.env matters now, and only for GitHub API work from the container. project_read it and write it to /mnt/project/GitHub.env with the Write tool (a bash heredoc carrying a secret trips the permission classifier), or skip it when the task touches no GitHub API.

Pinning

MUNINN_UTILS_REF defaults to main; the point of cloning is that changes land on the next cold boot with no version bump. Pass a SHA to test an unmerged state. rm /home/claude/.muninn-booted forces a re-pull in a warm container.

This file and boot.sh are the one thing that cannot self-update: the running copy is whatever the session mounted (project upload or marketplace sync), so a change here needs a push to both muninn-utilities/muninn-boot and the claude-skills/muninn-boot mirror, with metadata.version bumped.

© oaustegard, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in muninn-boot of oaustegard/claude-skills.

  • SKILL.md
  • CHANGELOG.md
  • scripts/boot.sh

Open the folder on GitHubat commit cf49d47

Compare with similar skills

Muninn Boot 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.

Muninn Boot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Muninn Boot this skilloaustegard/claude-skills150—~1.1kAutomated safety check: PassMIT
ComposioComposioHQ/composio30k1 repos~1.7kAutomated safety check: PassMIT
Connect Apps with ComposioComposioHQ/awesome-claude-skills77k3 repos~557Automated safety check: PassNone
Openloomi Connectorsmelandlabs/openloomi1k—~3.3kAutomated safety check: PassApache-2.0
Composio Cloud Toolsquarqlabs/argus279—~543Automated safety check: PassApache-2.0
GitHub Automationdavila7/claude-code-templates32k5 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Composio

    ComposioHQ/composio

    Route and complete Composio work across Composio For You and Composio Platform.

    30k GitHub starsUsed in 1 repo~1.7k tokens
    Productivity & AutomationAuto-check passed
  • Connect Apps with Composio

    ComposioHQ/awesome-claude-skills

    Connects an agent to 1000+ external apps through the Composio Tool Router plugin, so it can actually send emails, create issues and post messages instead of only drafting them.

    77k GitHub starsUsed in 3 repos~557 tokens
    Productivity & AutomationAuto-check passed
  • Openloomi Connectors

    melandlabs/openloomi

    openloomi Connectors tools - manage the native 7 messaging integrations and pair with the composio skill for the 1000+ apps OAuth layer (Slack, Discord, X, Gmail, Outlook, Google…

    1k GitHub stars~3.3k tokensUpdated 16 days ago
    Productivity & AutomationAuto-check passed
  • Composio Cloud Tools

    quarqlabs/argus

    Routes requests to external SaaS apps such as GitHub, Gmail, Google Calendar, Slack, Notion and Linear through cloud tools, with safeguards on irreversible actions.

    279 GitHub stars~543 tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • GitHub Automation

    davila7/claude-code-templates

    Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio).

    32k GitHub starsUsed in 5 repos~2.8k tokens
    Productivity & AutomationAuto-check passed
  • RollingGo Hotel Booking

    RollingGo-AI/rollinggo-hotel-skill-cn

    Searches hotels, checks live room prices, books and cancels reservations through the RollingGo rgh command-line tool, with confirmation steps for paid actions.

    163 GitHub stars~1.7k tokensUpdated 18 days ago
    Productivity & AutomationAuto-check passed

More from oaustegard/claude-skills

All 66 skills in this repo
  • Vega-Lite Interactive Charts

    oaustegard/claude-skills

    Builds interactive Vega-Lite charts from uploaded data: analyzes the fields, picks five to ten fitting chart types, and produces a React artifact with the data embedded inline.

    150 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Single-File HTML Composer

    oaustegard/claude-skills

    Builds self-contained single-file HTML pages such as reports, decks, postmortems, flowcharts and prototypes from a small spec using a bundled Python composer and templates.

    150 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed
  • Declauding

    oaustegard/claude-skills

    Rewrites model-sounding prose into plain technical writing and checks that every claim survives, for PR text, docs, commit messages and similar drafts.

    150 GitHub stars~5.2k tokensUpdated yesterday
    Auto-check passed
  • Preact Developer

    oaustegard/claude-skills

    Guides building standards-based Preact apps with native-first choices, HTM syntax, import maps and vendored ESM, from single-file demos to larger builds.

    150 GitHub stars~4.6k tokensUpdated yesterday
    Auto-check passed
  • Bluesky Zeitgeist Sampler

    oaustegard/claude-skills

    Deprecated sampler that captures short windows of the Bluesky firehose, clusters trending terms and builds an HTML report; replaced by the browsing-bluesky skill.

    150 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Adversarial Review Before Shipping

    oaustegard/claude-skills

    Has a fresh-context adversary attack a blog post, recommendation, analysis brief or piece of code before you ship it, using a profile suited to that kind of artifact.

    150 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Muninn Boot

What does Muninn Boot do?

Puts oaustegard/muninn-utilities on the container Python path — runs scripts/boot.sh, which shallow-clones the repo (codeload tarball as fallback) and writes the .pth. Muninn Boot is an agent skill from oaustegard/claude-skills.pth.

When should I use Muninn Boot?

Muninn Boot fits situations like: the first message of any new Muninn conversation; the user says boot up / boot — unless the message contains skip boot.

How do I install Muninn Boot in Claude Code?

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

How do I install Muninn Boot in Codex?

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

Can I use Muninn Boot 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 oaustegard/claude-skills --skill muninn-boot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/muninn-boot, .gemini/skills/muninn-boot, .github/skills/muninn-boot and .opencode/skills/muninn-boot in your project.

What does Muninn Boot need to run?

Going by SKILL.md and its folder, Muninn Boot needs a shell for the scripts in its folder, the command-line tools its instructions call (bash and git) and credentials named GH_TOKEN. Our summary lists: Python 3; A Bash shell.

Does Muninn Boot access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Muninn Boot safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Muninn Boot use?

Muninn Boot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Muninn Boot use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 Muninn Boot?

Skills that share tags, products or a category with Muninn Boot: Composio (ComposioHQ/composio, 30k stars), Connect Apps with Composio (ComposioHQ/awesome-claude-skills, 77k stars), Openloomi Connectors (melandlabs/openloomi, 1k stars) and Composio Cloud Tools (quarqlabs/argus, 279 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Muninn Boot?

oaustegard (a GitHub user) maintains it in oaustegard/claude-skills, which has 150 GitHub stars. The repository holds 66 skills in this directory. The repository was last updated on October 8, 2026.

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