services

services is a command for Claude Code from gotempsh/temps. It costs 0 tokens per session (5,967 once invoked), scanned A, original, Apache-2.0.

A command group for managing external services such as databases, caches, and storage connected to projects.

In plain words
What is it for?
Creating, linking, starting, stopping, updating, monitoring, backing up, restoring, and importing external services.
Why use it?
It centralizes the setup and operation of supporting services that an application depends on.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Creating, linking, starting, stopping, updating, monitoring, backing up, restoring, and importing external services.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gotempsh/temps/services
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.

Clone the repo
git clone --depth 1 https://github.com/gotempsh/temps

Made for: Claude Code.

Wrote 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.

agentmods badge for services

README.md
[![agentmods](https://agentmods.dev/badge/commands/gotempsh/temps/services/github.svg)](https://agentmods.dev/commands/gotempsh/temps/services)
Your own site
<a href="https://agentmods.dev/commands/gotempsh/temps/services"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/services/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.

agentmods 80×15 button for services

Your own site · 80×15
<a href="https://agentmods.dev/commands/gotempsh/temps/services"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/services.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.05967
Opus 5.5 $0.00000 $0.02387
Sonnet 5.5 $0.00000 $0.01193
Haiku 4.5 $0.00000 $0.00597

Measured 13d ago against content hash cb27f16180ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

services 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 13d 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.

skills/temps/references/commands/services.md · 637 lines

How it starts

The opening of the file, as written. The whole thing — 637 lines — stays where its author put it; the contents beside it link to each section on GitHub.

services command reference

Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.

Contents

services (alias: svc)

Manage external services (databases, caches, storage)

Subcommands:

  • list (ls) - List all external services
  • create (add) - Create a new external service
  • show - Show service details
  • remove (rm) - Remove a service
  • start - Start a stopped service
  • stop - Stop a running service
  • types - List available service types
  • projects - List projects linked to a service
  • update - Update a service
  • upgrade - Upgrade a service to a newer version
  • repoint-continuous-archive-source - Repoint a Postgres/MariaDB service's continuous archiving (WAL-G, or MariaDB's binlog shipper) to a different S3 source. Data archived before this call stays under the previous source and will no longer be verifiable or replayable once archiving points at the new one.
  • import - Import an existing external service
  • link - Link a service to a project
  • unlink - Unlink a service from a project
  • connect - Get connection info for a service by name or slug
  • env - Show environment variables for a linked service
  • env-var - Get a specific environment variable
  • logs - View persisted logs for an external service
  • slow-queries - Show slowest PostgreSQL queries from pg_stat_statements
  • enable-pg-stat-statements - Enable pg_stat_statements on a standalone Postgres service by restarting its container (drops active connections briefly)
  • metrics - Resource and engine metrics for a database/cache/storage service
  • restore-capabilities - Show what restore modes a service supports (in-place / new service / PITR)
  • list-backups - List backups stored on an S3 source
  • restore - Restore a service from a backup (in-place, new service, or PITR)
  • restore-runs - List recent restore runs for a service
  • restore-run - Show a single restore run
  • restore-cancel - Cancel a restore run that has not started writing data yet (refused once it has)
  • import-data-availability - Show whether a service can receive data imported from an external database, and what source it accepts
  • import-data - Copy a database from an external server into a database of this service (PostgreSQL, MariaDB/MySQL, MongoDB, Redis)
  • import-data-runs - List data imports into a service, newest first
  • import-data-run - Show one data import: outcome, phase, timings, who started it and the transfer output
  • import-data-cancel - Cancel a running data import (refused once the data has been copied)
  • wal-health - Probe a PostgreSQL service's WAL / archive_command health right now (archiver failures, backlog, stale replication slots) — diagnoses "Cloud backup mirror unavailable ... check that PostgreSQL's archive_command is succeeding" warnings

Read the full file on GitHub · 637 lines

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.

  1. 13d ago Changed · +90 lines cb27f16180ae
  2. 15d ago Changed · +1 lines 618ba836f866
  3. 1mo ago Changed · +13 lines 3122cc6f533a
  4. 1mo ago Changed · +13 lines 0d9a7e467078
  5. 1mo ago Changed b5fcc0199075
  6. 1mo ago First seen · 520 lines · 0 tokens per session scan A 5cf37979fadb

Subscribe to this mod's changes

services is a command published in the GitHub repository gotempsh/temps (861 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,967 tokens. 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 2026-09-03.

Related

Other commands, from other repositories