Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/kobiton/automateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/kobiton/automate/setup)<a href="https://agentmods.dev/commands/kobiton/automate/setup"><img src="https://agentmods.dev/badge/commands/kobiton/automate/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/kobiton/automate/setup"><img src="https://agentmods.dev/badge/commands/kobiton/automate/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.02380 |
| Opus 5.5 | $0.00008 | $0.00952 |
| Sonnet 5.5 | $0.00004 | $0.00476 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kobiton Automate Setup
Bootstrap the plugin: ensure the CLI wrapper symlink is installed, then have the bundled write-credentials.js script fetch the user's Kobiton credentials and write them to ~/.kobiton/.credentials. The API key goes straight from Kobiton to the file: it never appears in a tool result, a command you run, or your replies. After writing, recommend running /automate:doctor to verify.
Step 0: Ensure the CLI wrapper is installed
The run-interactive-session skill depends on ~/.kobiton/bin/kobiton. Claude Code and Codex CLI both recreate this wrapper automatically via a bundled SessionStart hook; on Codex, the user trusts the hook once via /hooks after install. This command (/automate:setup) re-installs the wrapper on demand. GitHub Copilot CLI and Gemini CLI also load /automate:setup (Copilot via Claude-format .md, Gemini via the bundled TOML at commands/automate/setup.toml) — neither has a SessionStart hook, so users on those CLIs run /automate:setup once after install. Cursor CLI loads this same .md via the commands field in .cursor-plugin/plugin.json, but registers it without the plugin namespace (it appears as /setup, distinguishable from Cursor's built-in /setup by its Kobiton description) and does not run the SessionStart hook - so Cursor CLI users also run this command once after install.
Run the install script bundled with this plugin. This file (setup.md) lives at <plugin-root>/commands/setup.md, so the install script is at <plugin-root>/scripts/install-cli.sh. Resolve <plugin-root> to its absolute path and run:
bash <plugin-root>/scripts/install-cli.sh
The script is idempotent. On first run it downloads the CLI build pinned by this plugin release from public.kobiton.download (sha256-verified, cached under ~/.kobiton/cli/) — that needs network access once; every later run is a cache hit with no network I/O. It then installs the ~/.kobiton/bin/kobiton entry point (a symlink to the plugin's wrapper on macOS/Linux, a bash exec-shim on Windows). Supported platforms: macOS on Apple Silicon, Linux x64, Windows x64 (Git Bash). After it returns, sanity-check the result:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 20d ago Changed 241c33f1967c
- 1mo ago Changed · -39 lines 805adb497b73
- 2mo ago First seen · 188 lines · 21 tokens per session scan A 61731b421b36
setup is a command published in the GitHub repository kobiton/automate (14 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 2,380 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
setup compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupkobiton/automate | Command | 14 | 4d ago | MIT | A | 21 | Claude Code |
| alignApexIQ/skillsmith | Command | 5 | 7mo ago | MIT | A | 0 | Claude Code |
| deploy-checklistApexIQ/skillsmith | Command | 5 | 7mo ago | MIT | A | 0 | Claude Code |
| lintApexIQ/skillsmith | Command | 5 | 7mo ago | MIT | A | 0 | Claude Code |
| migrateApexIQ/skillsmith | Command | 5 | 7mo ago | MIT | A | 0 | Claude Code |
| reportApexIQ/skillsmith | Command | 5 | 7mo ago | MIT | A | 0 | Claude Code |
| contextApexIQ/skillsmith | Command | 5 | 7mo ago | MIT | A | 0 | Claude Code |