Loadout

Loadout

Agent extensions, under control.

The package manager for your AI coding setup. Discover broadly. Activate the right tools for each project. Stay current without starting over.

Install · Why Loadout · Profiles · Discover · Trust · Commands

Install

You need Node.js 20 or newer and Git.

npm install --global loadout-ai@0.5.9
loadout setup --mode stable

The second command detects your agents and previews the 30-skill Stable loadout. Nothing changes until you approve it. If anything goes wrong, start with the [user test guide](./docs/USERTESTGUIDE.md).

How it works

Choose -> Inspect -> Preview -> Apply -> Undo

1. Choose Stable, Power, Maximum, or your own package list.
2. Inspect where each extension comes from and what it can do.
3. Preview every planned change without changing agent files.
4. Apply with --yes; Loadout saves a rollback snapshot first.
5. Undo with loadout rollback if you change your mind.

Abridged terminal transcript

This is an explicitly abridged transcript from a disposable, single-Codex Stable run. A literal … marks omitted fetch output; `` is a variable placeholder because snapshot IDs vary.

$ loadout setup --mode stable --agents codex
…
Loadout: Stable Boost
Detected agents: Codex
Catalog selection: 4 repositories
Ready to install: 4 skill repositories (30 agent skill directories)
Preview complete; nothing was changed. Re-run with --yes to install this exact screened plan.

$ loadout setup --mode stable --agents codex --yes
…
Loadout installed 4 repositories for 1 agent(s). Snapshot: 

$ loadout rollback
Restored snapshot 

The final preview sentence above is captured CLI wording. A later --yes invocation recomputes the plan from pinned sources and current agent and filesystem state; it does not persist or prove identity with the earlier preview.

Preview may fill Loadout's private download cache, but it does not change your agent files. Review the summary and warnings before approving an apply command.

Why Loadout

Loadout started with a frustrating question: why does improving an AI coding agent still mean opening twenty GitHub tabs?

Useful skills, plugins, MCP servers, and settings arrive one experiment at a time. Soon it is hard to remember what is installed, where it came from, whether something better launched yesterday, or how to undo a change. The name comes from games, where your loadout is the set of tools you choose for the mission. This does the same for AI coding agents without making you rebuild the setup for every agent and every project.

Most extension tools begin with a repo you already know. Loadout begins one step earlier: what is actually worth knowing? It stays with you after installation.

Loadout watches a much wider catalog than it activates. You can keep thousands of technically screened skill copies in the disabled Maximum library, discover new projects as they appear, and let each codebase pull a focused active set instead of dumping everything into every prompt.

| The usual workflow | The Loadout workflow | | -------------------------------------------------------------- | ---------------------------------------------------------------- | | Find recommendations across feeds and bookmarks | Watch one growing discovery catalog | | Open every repo and guess whether to trust it | Inspect pinned sources, licenses, components, and risk findings | | Copy skills separately into Claude, Codex, Cursor, and friends | Apply one reviewed selection across detected agents | | Let every skill compete for context forever | Keep a bounded daily set or activate skills for this project | | Hope updates do not break anything | Preview updates and protect every managed change with a snapshot | | Manually remember what was changed | Scan, reconcile, remove, roll back, or completely uninstall |

Loadout is local, open source, and preview-first. It does not need an OpenAI or Anthropic API key to manage skills. MCP servers and executable tools stay behind their own explicit setup and permission steps.

Demo

Watch the 72-second Loadout demo on YouTube. It shows the real CLI product, including profiles, project-aware selection, discovery, explicit integrations, and snapshot-backed rollback. The exact [recording and voiceover script](./docs/DEMOSCRIPT.md) is public.

The [end-to-end acceptance guide](./docs/USERTESTGUIDE.md) contains the commands you can run yourself.

Stable workflow

Stable Boost: install the essentials and start building

Stable is the recommended daily driver: 30 selected skill directories from four pinned public sources, installed into each agent you choose. It covers planning, implementation, debugging, testing, documentation, code review, frontend work, performance, Git, shipping, and more without turning every discovered skill on.

| Included source | What Stable takes from it | GitHub | | ---------------------------------------------------------------------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | | Superpowers | Planning, execution, testing, review, verification | [](https://github.com/obra/superpowers) | | Context7 | Current documentation and MCP workflows | [](https://github.com/upstash/context7) | | Addy Osmani Agent Skills | Engineering, frontend, debugging, performance, docs, shipping | [](https://github.com/addyosmani/agent-skills) | | Agent Skills Marketplace | Architecture, review, error handling, JavaScript, Python | [](https://github.com/wshobson/agents) |

Every row links directly to the upstream project. Loadout does not claim ownership or endorsement; it pins, credits, screens, and selects from their public work.

# Preview for detected agents
loadout setup --mode stable

# Recompute from current state and apply after reviewing the preview
loadout setup --mode stable --yes

# Inspect managed state, then undo the install if needed
loadout status
loadout scan
loadout rollback

Stable is Loadout's strongest general starting point, not a claim that one setup is best for every person or project. Run loadout profiles stable --json when you want the machine-readable selection.

Manage skills you already have

Already have skills? Loadout can compare them with exact catalog copies and manage the ones it can identify confidently:

# Read-only inventory and source/update comparison
loadout scan
loadout reconcile --refresh

# Record ownership only for exact byte-for-byte matches; files are not rewritten
loadout reconcile --yes

# Preview old copies that have one unambiguous reviewed source
loadout reconcile --replace-outdated

Unknown or ambiguous copies stay untouched. Replacing an old copy is a separate, previewed transaction with its own rollback snapshot. Managed copies can then be checked by loadout update without moving them to a different agent path.

Profiles

Loadout is opinionated when you want it to be and precise when you do not.

Power Boost: a larger cross-project toolkit

Power draws a skill-level allowlist from eight major collections. The prepared set is deduplicated and invalid units are quarantined, so the final count can be lower than the raw allowlist. In current acceptance testing it prepared about 50 active skills per agent.

| Included source | Focus | GitHub | | ------------------------------------------------------------------------ | --------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Anthropic Skills | Documents, frontend, MCP building, web testing | [](https://github.com/anthropics/skills) | | OpenAI Skills | CLI, docs, browser work, images, security | [](https://github.com/openai/skills) | | Vercel Agent Skills | React, web design, composition, deployment | [](https://github.com/vercel-labs/agent-skills) | | Superpowers | Planning, debugging, testing, collaboration | [](https://github.com/obra/superpowers) | | UI UX Pro Max | UI systems, slides, styling, product design | [](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) | | Context7 | Current documentation and MCP workflows | [](https://github.com/upstash/context7) | | Agent Skills Marketplace | Architecture, testing, APIs, TypeScript, Python | [](https://github.com/wshobson/agents) | | Awesome Copilot | Codebase knowledge, plans, browser and security workflows | [](https://github.com/github/awesome-copilot) |

loadout setup --mode power

Maximum Library: download broadly, activate intelligently

Maximum is for explorers. It downloads every non-archived, technically screened skill component in the catalog into Loadout's disabled local library. Disabled means cached and available, not injected into agent context. Then let the current project choose a focused active set:

loadout setup --mode maximum
loadout recommend --project . --agent codex
loadout optimize --project . --agents codex,claude-code --limit 30
loadout optimize --project . --agents codex,claude-code --limit 30 --yes

This is the difference between “install everything” and “have everything ready.” The first overloads agents; the second gives you a large library with a small, relevant active loadout.

Custom: take exact control

Use setup when the listed packages should become the complete managed profile for the selected agents. Packages from the previous managed profile that are not listed will be retired, and the preview names every retirement:

loadout setup --mode custom --package superpowers --package context7

Use install when you only want to add a package without replacing the current managed profile:

# Install the reviewed Humanizer writing skill into Codex
loadout install --mode custom --package humanizer --agents codex

# Install the reviewed Obsidian skills explicitly
loadout install --mode custom --package obsidian-skills --agents codex,claude-code

Run loadout profiles to compare every mode. MCP servers always use a separate approval step. Obsidian skills are also proposed automatically when recommend or optimize detects an Obsidian vault; they are not added to the universal Stable set.

MCP integrations

Profiles never start MCP servers silently. First list the available recipes and see which ones need credentials:

loadout mcp-recipe
loadout mcp-recipe --credential-free

Preview and configure one for the host you use:

loadout mcp-recipe playwright --agent codex
loadout mcp-recipe playwright --agent codex --yes
loadout mcp-recipe playwright --agent codex --verify

loadout mcp-recipe playwright --agent claude-code
loadout mcp-recipe playwright --agent claude-code --yes

Configuration alone does not start the server. Test a real connection separately with --connect --approve-risk. Loadout can reference credentials from environment variables or the OS keychain without printing their values.

Optional runtime tools

Graphify is an optional codebase graph tool. It installs both a command and an agent skill, so Loadout keeps it separate from the normal profiles. It does not require an OpenAI or Anthropic API key:

loadout tool graphify --agents codex,claude-code
loadout tool graphify --agents codex,claude-code --yes --approve-risk
loadout tool graphify --remove --agents codex,claude-code --yes --approve-risk

Executable tools remain an explicit choice instead of hiding inside a profile.

Catalog and discovery

GitHub moves every day. Your loadout should not stand still.

The catalog is not a frozen “top 50” list. Loadout separates discovery from installation so a viral repo can be noticed quickly without being trusted blindly. Candidates enter a review queue; catalog entries are pinned and inspected; only the bounded Stable policy gets the strongest automatic recommendation.

# Find candidates across configured discovery sources
loadout discover --source all --queue

# Inspect the queue and one candidate before promotion
loadout review-queue
loadout candidate inspect owner/repository

# Check whether managed active or disabled-library sources changed
loadout update
loadout health --updates

Daily checks are opt-in and read-only. They tell you what changed; they do not silently rewrite your agents:

loadout autopilot --yes
loadout autopilot --status

The bundled catalog currently contains 53 credited public repositories across 39 categories: 34 have skill components and 19 are MCP-only. All 53 are technically screened and pinned; 4 sources are selected by the bounded Stable policy. See every linked source, license status, component type, and pinned commit in [Catalog and upstream credits](./docs/CATALOG.md).

Catalog maturity: 53 sourced, 53 technically inspected, and 4 selected for Stable. Independent human-review attestations and signed comparative benchmarks are not yet published, so Loadout does not pretend static inspection proves usefulness. The pinned catalog remains usable today, and local outcomes can be recorded to improve later rankings. Definitions and promotion rules are in the [catalog policy](./docs/CATALOG_POLICY.md).

Loadout does not claim there is one universally “best” configuration. Recommendations are bounded, rule-based proposals; stars and discovery results are signals for review, not quality proof.

Discovery snapshot (generated 2026-07-22): [240 repositories observed](./docs/DISCOVERED.md), including 216 uncataloged review candidates and 24 repositories already in the inspected catalog.

The checked-in discovery report proves only its dated snapshot, not the success of every scheduled run. Use `loado

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: VirajMishra1
• Source: VirajMishra1/loadout
• License: MIT
• Homepage: https://www.npmjs.com/package/loadout-ai

Install and usage instructions live in the source repository linked above.