Deploying AI agents for clients is a job now.
This is its toolkit.
From your first installed skill to a paying client's self-maintaining fleet — one open-source platform for the whole path. Pick the station you're standing on.
What are your agents missing? One command scans your local Claude/Codex/Hermes/OpenCode installs and diffs against the catalog.47
MCP tools — search, install, publish, fleet
61
skills hosted here, versioned + signed
99,000+
skills indexed across federated registries
0 humans
agents enrol themselves (Ed25519)
Open source (MPL-2.0) · Free tier · Self-host the whole thing · Cancel anytime
The path · click a station
You have an agent. Give it a supply chain.
Day 1 costs nothing and needs no account. Point your agent at the registry, and it can search, install and run vetted skills from inside its own conversation — one MCP surface instead of forty copy-pasted markdown files.
A · the one-liner
Tell your agent this. That is the whole install — no package to add, no key to paste.
"Install the loopskill skill from app.loopskill.io/skill"
Per-agent install guide — Claude Code, Codex, Cursor, Cline, Hermes, OpenClaw B · not ready to sign up? Look at what you already have
loopskill import and
loopskill diff read the skills already sitting in
~/.claude, ~/.codex,
~/.cursor and ~/.hermes, and show you
exactly how two machines have drifted. Zero network calls —
enforced structurally, not promised: the network-capable module is one the offline commands never import,
and a test breaks socket.socket for their duration to prove it.
What day 1 actually buys you
- · One search surface over this catalog and 99,000+ skills indexed across federated registries — we link to those, never rehost them.
- · Skills that ship a runnable loop: press run, get an objective pass/fail under enforced bounds. Not a model's opinion.
- · Nothing to un-pick later. Everything below is the same platform, no migration.
Hand them one line. Keep your name on it.
A bundle is the unit of client work: the skills that client's agent should have, pinned at exact versions. You edit the bundle; their agent pulls. There is no push — the control plane cannot reach into a client machine, which is precisely why a client will let you near theirs.
-
step 01
Compose the bundle
Pick skills, pin versions, name it after the client. Or fork someone else's public stack and start from a working set instead of a blank page — preview the diff before you claim it. Compose one →
-
step 02
Scope a key to that bundle, and nothing else
A bundle-scoped key (
cbt_…) reaches exactly one bundle. If a client leaks it, they leak that bundle — not your catalog, not another client. Key scopes → -
step 03
Send the install line
One line, branded-neutral, key already baked in. Their agent installs and then reconciles on its own schedule — no dashboard for them to babysit, no LoopSkill branding on their side. Delivery guide →
Fork one of these instead of starting empty
All →Before you run someone else's code on a client's machine
- · Skills can run in an ephemeral, syscall-audited sandbox with a network allowlist.
- · Anonymous contributions land as drafts and need a human reviewer before promotion.
- · Packs are content-addressed: the same source rebuilds byte-identical, sha256 verifiable.
Your second client is where it breaks.
One client, one agent — easy. Two clients, five agents, and nobody knows which version of which skill runs where. A bundle lock is an immutable revision; every agent reports a three-way verdict against it — declared vs installed vs extras. Drive the matrix below.
| agent | copywriting declares 1.0.0 | humanizer declares 2.1.1 | agentic-os declares 1.0.0 | Super Memory declares 1.0.2 | ruthless-mentor declares 1.0.1 | action |
|---|---|---|---|---|---|---|
| acme-prod-01 | ||||||
| acme-prod-02 | ||||||
| northwind-01 | ||||||
| northwind-02 | ||||||
| solo-laptop |
Hover, focus or click any cell to inspect it — or hit Converge on a drifted row.
·
- declared
- installed
- extras
The state above is simulated so you can drive it without an account. The skills named are real catalog entries — click one. Your own matrix lives behind sign-in: Your Library → Fleets · how locks and the three-way verdict work. Known gap, stated rather than hidden: an assignment that has never run once still reads healthy at the top level — see what LoopSkill does and does not do.
Immutable lock revisions
Edit a bundle and a new revision is minted. Every agent's verdict is computed against a specific revision, so "which version did they actually get" has an answer, not a guess.
Agents enrol themselves
An agent proves possession of an Ed25519 key and registers itself. No OAuth screen, no session, no human clicking through a console on a client's laptop. How →
Convergence is a poll, not a push
Nothing is pushed to a client machine and nothing is real-time — an agent reconciles on the schedule you install. That is a security property, and we would rather state the interval than call it "instant".
Run a Fleet — the curriculum for this station
A multi-agent setup with shared memory, loop-safe Discord coordination, and per-client reporting.
Open the trackThe runbook you already wrote is the product.
Three ways the work you're already doing turns into revenue — none of them require you to stop doing client work.
01 · publish
Turn a workflow into a skill
Describe the runbook in plain language and one call scaffolds a SKILL.md draft. It goes through a quality gate and a human review before it's listed — the same gate everyone else's does.
Creator workflow02 · refer
50% recurring, then 30%
Refer a Pro subscriber and earn 50% of every invoice they pay for your first 50 referrals, 30% after — monthly, for as long as they stay. Paid out via Stripe Connect.
Referral terms03 · hand it off
Or don't run it yourself
If a client wants the outcome and not the operations, WiseChef runs the same stack as a managed service. Same skills, someone else's pager.
Publish or get helpWhat it costs to run this
The whole platform is MPL-2.0 — clone it, docker compose up, run
every capability on your own hardware with no account and nothing phoning home. Pro is hosted
convenience, never a feature gate.
See the ladder →
Popular skills
Browse all →copywriting
general · 41
humanizer
general · 52
agentic-os
automation · 4
Super Memory
automation · 103
ruthless-mentor
ops · 11
Coldstart Bench 20260908 B8C56156
productivity · 3
elevenlabs-pro
productivity · 7
hundred-million-offers
marketing · 7
critical-code-reviewer
code-review · 7
ascii-video
marketing · 8
clean-code
code-review · 6
musk-5-step-algorithm
automation · 12
What fills the bundles
A small signed core, inside a very large index.
The curated catalog is deliberately small — every entry is audited and signed. Around it sits a federated index of everything else worth finding. We link to indexed skills; we never rehost them, and we never count them as ours.
61
curated here
Audited on every push, ed25519-signed delivery, version-pinned in bundles.
99,000+
indexed, federated
Searched across upstream registries in one query, with an honest per-source breakdown of what is indexed vs actually installable.
3,120
MCP servers indexed, review-gated
Discovered and staged behind a human review gate. Staging is not publishing — you cannot browse or install these yet, and the scope doc says so plainly.
Works with every
major AI agent
Before you bet a client on this
We publish what this does not do.
You are about to put this between you and someone who pays you. A marketing page that only lists wins is not enough information to make that call, so there is a page that lists the gaps — known blind spots, half-shipped surfaces, and the exact probe behind every "verified" claim.
Example: the never-run blind spot
The fleet view shows which assignments converged and which are failing. It does not yet age a never-run assignment into an alarm — a loop assigned and never fired looks healthy at the top level. That is on the scope page, not buried in a changelog.
Every number on this page is live
The counts above are fetched from public endpoints when this page is built, and any stat that cannot be fetched is omitted rather than guessed. Check them yourself: the API reference lists the endpoints they come from.