services

A command for managing trusted API services and database connections used by the connect service. It stores credentials, controls read-only or write access, and manages which destinations are allowed.

In plain words
What is it for?
Use it to register services, set authentication, choose write permissions, manage the destination allowlist, and check trust status.
Why use it?
It gives access rules around external services instead of sending credentials or allowing unrestricted connections.

Command

Part of the goodvibes plugin — 6 skills, 5 commands, 4 agents, 9 hooks, 3 MCP servers shipped together

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/mgd34msu/goodvibes-plugin/services
Clone the repo
git clone --depth 1 https://github.com/mgd34msu/goodvibes-plugin

Or install goodvibes, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 4 agents, 9 hooks, 3 MCP servers.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,562 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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01562
Opus 5 $0.00016 $0.00781
Sonnet 5 $0.00007 $0.00312
Haiku 4.5 $0.00003 $0.00156

Measured 3d ago against content hash cf224cfb745b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

plugins/goodvibes/commands/services.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Services (connect trust boundary)

Manage the registry that the connect server uses for authenticated HTTP and database access. All registry operations go through the single mcp__connect__service tool; this command is a thin, guided wrapper over its actions.

Trust invariants (enforced by the server, not this command):

  • Credentials are pinned to their registered origin (protocol + host + port) and never sent elsewhere, even in open mode.

  • The destination allowlist is on by default: registered service origins and explicitly allowlisted hosts only.

  • Read-only by default: a service opts specific HTTP methods in via write_methods; a connection opts writes in via allow_writes.

  • Open (unrestricted) mode is human-only and out-of-band. A person edits .goodvibes/config.json, and it is announced at session start. It reverts to restricted next session unless dangerously_persist_across_sessions is set. This command and the service tool cannot flip the trust mode.

  • set_auth stores secrets at mode 0600 and never echoes them back; no action ever returns a secret value. get returns an auth STATUS, list/status return names and summaries only.

Usage

/goodvibes:services                       # list registered services + connections + allowlist
/goodvibes:services status                # trust mode + persist flag + registered names + allowlist
/goodvibes:services list                  # registered service summaries and connection names
/goodvibes:services get <name>            # credential-free summary + auth status of one service
/goodvibes:services register <name>       # register an API service (guided)
/goodvibes:services remove <name>         # remove a service and purge its credentials
/goodvibes:services set-auth <name>       # store credentials for a service (0600, never echoed)
/goodvibes:services set-url-pattern <name>       # map an extra hostname to a registered service
/goodvibes:services allow <hostname>      # add a destination host to the allowlist
/goodvibes:services unallow <hostname>    # remove a host from the allowlist
/goodvibes:services register-connection <name>   # register a DB connection (Postgres/MySQL/SQLite)
/goodvibes:services remove-connection <name>     # remove a DB connection

Read the full file on GitHub · 91 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. 3d ago First seen · 91 lines · 33 tokens per session scan A cf224cfb745b

Subscribe to this mod's changes

services is a command published in the GitHub repository mgd34msu/goodvibes-plugin (6 stars, last pushed 10d ago), licensed MIT. It adds 33 tokens to every session and 1,562 once invoked, about $0.0002 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.