A command that starts an OBTO session by checking identity, selecting the working domain, and setting the agent’s context. OBTO is the app-building and deployment platform used by the related plugin.

Use it at the beginning of an OBTO task to verify access, inspect available apps, and choose the correct tenant when the account can access more than one.

It establishes who is connected and which workspace or tenant the agent should use before other OBTO operations.

start — Command by obto-inc

Install

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.

agentmods

npx agentmods add commands/obto-inc/platform/start

Clone the repo

git clone --depth 1 https://github.com/obto-inc/platform

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 437 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00019	$0.00437
Opus 5	$0.00010	$0.00218
Sonnet 5	$0.00004	$0.00087
Haiku 4.5	$0.00002	$0.00044

Measured yesterday against content hash 7cb783e60d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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 yesterday.

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.

plugins/obto/commands/start.md · 15 lines

What it actually says

Initiate an OBTO working session. Arguments: $ARGUMENTS

This plugin configures one OBTO MCP server — obto (app.obto.co), the OBTO platform cluster.

Steps:

Call obto_whoami. Report back: identity, identityDomain (the identity's own tenant), the connection's default domain, serverVersion, and the available apps. If the call fails with an auth error, tell the user to approve the OAuth prompt for the server in their browser — Google sign-in; a first-time sign-in provisions their workspace automatically; authorize once and it's remembered.
Resolve the WORKING domain, then state the context. For super-users (whoami crossTenantEnabled: true, server 3.5.26+) the reported domain is only the connection vhost's default — NOT a boundary: any active tenant's domain may be passed per call, so one connection serves every tenant on the cluster. If the task names a tenant, confirm its exact slug against whoami's tenantDomains and use THAT as domain for the whole task — a typo'd slug is refused with unknown_domain + didYouMean. If the tenant is ambiguous, ask the user. Regular users are pinned to their own domain (cross_tenant_not_allowed). Then state the working context in one line — the working domain, and that every subsequent tool call carries appName + domain explicitly (the server is stateless; there is no active app).
Load the matching skill before touching anything: building/deploying ⇒ obto-build-loop / obto-deploy; local media or large files ⇒ obto-upload; publishing per-tenant MCP tools/resources/prompts ⇒ obto-mcp-extend; remembering/recalling context ⇒ obto-memory; anything failing ⇒ obto-troubleshooting.

Changes

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.

yesterday First seen · 15 lines · 19 tokens per session scan A 7cb783e60d16

Subscribe to this mod's changes

start is a command published in the GitHub repository obto-inc/platform (1 stars, last pushed 27d ago), licensed Apache-2.0. It adds 19 tokens to every session and 437 once invoked, about $0.0001 per session on Opus 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 2026-08-31.

Data and AI DevOps and cloud Planning ai-agents claude deployment-platform full-stack mcp mcp-server

release

Run the cabloy release workflow. Use when the user asks to "release", "publish", "deploy", "bump version", "create release", "release patch", "release minor", or "release major". Handles version bump, AI changelog generation, npm publish, and GitHub release creation.

cabloy/cabloy · 65 tokens

start

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

release

analytics

backups

environments

errors

dns-provider