Setup

Skill aylee/agent-os/.agents/skills/setup

Personalize or upgrade an Agent-OS instance only when the user explicitly invokes setup. Preview all writes, preserve fictional examples unless removal is approved, and never overwrite global runtime or third-party skill configuration.From its SKILL.md

Install

npx -y skills add aylee/agent-os --skill setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 353 tokens by cl100k_base, as published. Nobody here has run it

Set up Agent-OS

Safety preflight

Read agent-os.yaml, README.md, docs/setup-contract.md, and current identity/area/binder files.
Detect whether setup is fresh, partial, or an upgrade. If personal data already exists, create or request an out-of-band backup before bulk changes.
If a public upstream Git remote exists, warn before writing personal information and recommend a private copy or private fork. Git itself is optional.
Preview every file to create, update, tombstone, or leave untouched. Obtain confirmation before deleting or replacing examples.

Personalize

Gather the exact initializer answers first: instance name, profile name, owner display name, IANA timezone, and zero to ten active projects with stable slug, purpose, and start date.
Run the deterministic initializer in preview mode. Show its exact operations and token, then apply only after confirmation. The helper generates the instance UUID.
Update setup-owned files only. Create binders from library/templates/binder.md and link each active project to a compact workstream.
After the minimal instance validates, offer separate previewed passes for role, voice, and area context; do not make them prerequisites for initialization.
Put credentials, raw transcripts, caches, indexes, and private integration configuration in the external local-state directory keyed by the instance UUID. Never place them under the portable root, even if ignored by Git.
Treat integrations and tooling as optional capabilities with a documented manual fallback.

Finish with changed paths, skipped choices, validation results, backup location, and the first recommended action. Do not install global skills, symlink runtime settings, run package managers, or commit unless separately authorized.

What ships with it: 2 files

582 B alongside SKILL.md

agents/

agent-os.yaml310 B
openai.yaml272 B

Gives 0 of the 12 instructions most project setup skills give in 353 tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

Ask one question at a timein 29 of 999, across 28 files
Detect the package manager from lockfilesin 28 of 999, across 9 files
Present findings to the userin 26 of 999, across 5 files
Explore current repo statein 24 of 999, across 3 files
Update the agent skills block in place if it existsin 24 of 999, across 3 files
Install husky lint-staged and prettierin 23 of 999, across 4 files
Create the lintstagedrc filein 22 of 999, across 3 files
Commit all changed filesin 22 of 999, across 3 files
Run lint-staged to verify it worksin 22 of 999, across 3 files
Create the husky pre-commit filein 21 of 999, across 2 files
Create a prettierrc file if missingin 21 of 999, across 2 files
Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

read setup contract and identity files
detect fresh partial or upgrade setup
warn before writing to public remote
preview every file write
get confirmation before deleting examples
gather exact initializer answers first

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.