sno-cli — Claude Code skill: features and installation
The sno-cli Claude Code skill operates the sno command-line tool. It handles Sno product setup and checks, plus Station and REM tasks.
Apache-2.0 ★ 869 updated 2026-11-16
npx skills add sno-ai/sno-station-skills --skill sno-cli -a claude-codeWhat sno-cli does
The skill runs sno commands to install, update, or remove Sno products, inspect program and skill health, and handle account, Station, and REM operations. To find valid commands and flags, it reads help from the installed binary itself.
The skill needs shell access and an installed sno executable. It checks the result after a command that changes something, and runs machine-changing actions only when the owner requests them. The installed binary is the source for flags, not this skill file. If multiple executables turn up, it selects the newer path and tells the owner.
What it helps with
- install a Sno product with
sno setup - check program and skill health with
sno doctor - see the remaining model allowance with
sno usage - change Station telemetry consent
- run REM commands to judge or retrieve a result
Example prompts for the agent
- Install a Sno product and check its health.
- Show the remaining model allowance.
- Check Station telemetry consent and show its current setting.
How to install sno-cli
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill sno-cli -a claude-code2Manually: put the files in place
~/.claude/skills/skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skill/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill sno-cli -a codex2Manually: put the files in place
.agents/skills/skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill sno-cli -a cursor2Manually: put the files in place
.cursor/skills/skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sno-ai/sno-station-skills skills/M-build-and-rollout/sno-cli/skill2Manually: put the files in place
.github/skills/skill/SKILL.md1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill sno-cli -a gemini-cli2Platform CLI
gemini skills install https://github.com/sno-ai/sno-station-skills --path skills/M-build-and-rollout/sno-cli/skillManually: put the files in place
.devin/skills/skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill sno-cli -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about sno-cli
How do I install sno-cli in Claude Code?
Run npx skills add sno-ai/sno-station-skills --skill sno-cli -a claude-code. The skill file is available at ~/.claude/skills/skill/SKILL.md.
What does sno-cli do?
It operates the sno utility for product setup and removal, health checks, and account, Station, and REM tasks. It gets command flags from the installed version's help output.
What does sno-cli need to run?
It requires shell access and an installed sno executable. The skill uses that binary to read its command help and flags.
Source text
SKILL.md · Apache-2.0
---
name: sno-cli
description: >-
Operate the `sno` command-line tool: install, update, check, and uninstall Sno
products, read the exact commands and flags of the installed version, and run the
account, skills, onboarding, Station telemetry and REM commands. Use when the owner or
a task says "sno", "Sno CLI", "sno setup", "sno update", "sno doctor",
"sno uninstall", "sno station", "telemetry consent", "rem verdict", "sno account",
or "sno skills". The exact flags always come from the installed binary, never from
this file. Do not use it to decide the owner's choices for them.
requires:
programs: []
harness:
- {slot: 4.shell, need: required}
---
# Sno CLI
`sno` is one binary. This file carries the rules, the task map and the recipes. The exact
commands and flags of the version that is installed are served by the binary itself, so they
cannot be out of date.
## Start Here
Choose the executable once and keep using it:
- Use the absolute path the installer printed.
- Otherwise run `type -a sno` (works in bash and zsh). If two `sno` files are listed, or the version is older
than the installer said, tell the owner, use the newer absolute path, and note that a
running shell may need `hash -r` or a new terminal.
- If `sno` is not installed, say so. Do not look for its source.
In every command block, `sno` stands for that absolute executable. Then read the reference
for this exact version, once:
```text
sno --version
sno
```
`sno` alone prints the list of commands. Before you use a command, read `sno <command> --help`
(for a nested command, `sno <group> <command> --help`). That output comes from the installed
binary, so it is the authority for every flag.
## Conventions
- Pass `--json` when you parse the output. Stdout is then exactly one JSON value.
- A command you typed incompletely or inexactly is completed, or answered, instead of failing:
- Unique prefixes of subcommands and flags work: typing sno stat runs sno station.
- A missing value gets a default, and a note says which (`notes` in JSON, the first line in text).
- When nothing sensible can run, you get guidance: a JSON object with `"usage": true` and
`"executed": false`, or full help plus an example, and the exit code is 0. A normal result has
no `executed` field; a missing `executed` means the command ran.
- After a command that is meant to change something, read the result before you tell the owner it
worked. A value that does not match is not applied: for example `sno station consent`
with a misspelled level only shows the current level and a note, and the exit code is still 0.
Check that the returned value is the one the owner chose, and that `executed` is not `false`.
- A real failure keeps a non-zero exit code and its message says what to do next. Report that
message to the owner; do not retry in a loop.
- Anything that changes the machine is run only when the owner asked for it.
## Sno GPU attribution
When a Sno command invokes Sno GPU, keep the real project/session/run context in the
command's supported inputs; read its installed help before choosing flags or JSON fields.
For RSI, `sno rem judge` already accepts a run with per-session project context and
`sno rem recall` accepts `project_id`. Do not relabel a mixed-project run as the shell's
current repository, invent attribution flags, or call GPU/Helicone directly to bypass Sno.
The component sending GPU HTTP must supply its own repository slug as `X-Sno-Source`, the
stable feature workload (`rsi` for RSI) as `X-Sno-Workload`, and a fresh UUID v4 as
`X-Request-ID` generated inside every attempt, including retries, never in static client
headers. New repositories and workloads need no registration or approval. The sender must
record status or failure with that ID and preserve existing operation IDs. Authentication/admission supplies verified user
and machine identities; never add caller-supplied user/machine identity headers. Missing
diagnostic context is recorded as unknown without rejecting valid model work. These rules
also apply to future GPU-backed commands; the full caller contract is in the skill library's
`skills/README.md`. Other model providers and health/model-list probes keep their own behavior.
## Task map
| Task | Command |
|---|---|
| Install the default product, or a chosen one | `sno setup`, `sno setup <product>` |
| Update the CLI and installed products | nothing to run: any `sno` command updates first when a newer release is out |
| Health of programs, skills and Station | `sno doctor` |
| Project memory and improvement records | `sno project status`, `sno project list` |
| Remaining model allowance | `sno usage` |
| Uninstall | `sno uninstall`, `sno uninstall <product>`, `sno uninstall all` |
| Machine identity | `sno account register`, `sno account claim` |
| Agent instructions served by the binary | `sno skills`, `sno skills <name>` |
| Reply to an optional product offer | `sno products` |
| Configure and prove Station | `sno onboarding status`, `sno onboarding apply`, `sno onboarding verify` |
| Telemetry choices and export | `sno station consent`, `pause`, `resume`, `export` |
| Verify a stored event | `sno station audit` |
| Local REM jobs | `sno station rem-start`, `sno station rem-status` |
| REM runs and verdicts | `sno rem judge`, `sno rem recall`, `sno rem verdict` |
Flags are not listed here on purpose; read them from `sno <command> --help`.
## Recipes
### Report a fresh install to the owner
```text
sno --version
sno doctor --json
sno skills core
```
Tell the owner the version, where it is installed, and the one next step. Station onboarding
questions and product offers are put to the owner as questions; you never answer them.
### Check health
```text
sno doctor --json
sno project status --json
sno usage --json
```
`doctor` exits 0 on warnings. Read the rows whose result is `failed` or `missing` and relay
each with its fix. If `usage` says the machine is not registered, tell the owner and offer
`sno account register`.
### Update
Never ask the owner to run `sno update`. Any `sno` command that finds the CLI or an installed
product older than the latest release (checked once a day) updates first and then runs what was
asked. `sno update` exists for manual use only.
### Uninstall
```text
sno uninstall
sno uninstall sno-station
sno uninstall sno-station --yes
```
The first two only list and explain; nothing is removed. Uninstalling is the one action that is
asked about even when the owner just told you to do it, the same way `rm -rf` is: a request such
as "uninstall sno-station" is not the confirmation. Run the first two, show the owner what will be
removed, ask "Uninstall now?", and stop. Run the third only after the owner answers yes in a
later message. If there is no later message, your answer is the plan and the question.
`--purge-state` also deletes Reach mail state; ask for that separately.
### Local REM jobs
```text
sno station rem-start --type noop --scope persona:demo
sno station rem-status --wait --timeout 60
```
`rem-status` without an id reads the most recent job started on this machine.
## Owner-only actions
Ask the owner, and wait for the answer, before you:
- set a telemetry consent level (`sno station consent <level>`) or pause or resume it;
- record an answer to a product offer (`sno products <product> <answer>`);
- send a human verdict on a REM judgment (`sno rem verdict`);
- run `sno uninstall … --yes`, or `--purge-state` — even when the owner's own request was to uninstall.
Reading is always fine: `sno station consent` with no value, `sno products` with no arguments (it lists), `doctor`,
`usage`, `skills`, `project`.
© sno-ai · Apache-2.0 · sno-ai/sno-station-skills