integration-steward

integration-steward is an agent for Claude Code from Openly-Useful/operations-pulse. It costs 25 tokens per session (159 once invoked), scanned C, original, MIT.

An agent that evaluates optional tool connections and guides their setup with limited permissions and explicit consent.

In plain words
What is it for?
Choosing free or local connection options, requesting the smallest access scopes, testing safely, documenting credentials and data boundaries, and explaining how to disconnect.
Why use it?
It reduces security, cost, and data-exposure risks when connecting external services to an AI agent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/openly-useful/operations-pulse/integration-steward
Clone the repo
git clone --depth 1 https://github.com/Openly-Useful/operations-pulse

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 integration-steward

README.md
[![agentmods](https://agentmods.dev/badge/agents/openly-useful/operations-pulse/integration-steward.svg)](https://agentmods.dev/agents/openly-useful/operations-pulse/integration-steward)
Your own site
<a href="https://agentmods.dev/agents/openly-useful/operations-pulse/integration-steward"><img src="https://agentmods.dev/badge/agents/openly-useful/operations-pulse/integration-steward.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 159 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 5.1 $0.00025 $0.00159
Opus 5 $0.00013 $0.00079
Sonnet 5 $0.00005 $0.00032
Haiku 4.5 $0.00003 $0.00016

Measured 5d ago against content hash 9e461780c43a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

integration-steward scanned grade C with 1 finding 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 5d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

- Collect credentials only through the host's secure connection UI or secret
agents/integration-steward.md · 24 lines

What it actually says

Integration steward

Own connection contracts and setup guidance, not operator credentials.

Guardrails

  • Offer a free/local or self-hosted option first when practical.
  • Collect credentials only through the host's secure connection UI or secret store.
  • Request the smallest scopes and disclose writes, cost, and data boundaries.
  • Test against non-production or read-only resources first.
  • Do not enable a connector marked planned.

Output

Connection ID, need, setup modes, cost class, scopes, storage boundary, test, disconnect path, enabled tools, and unresolved security requirements.

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. 5d ago First seen · 24 lines · 25 tokens per session scan C 9e461780c43a

Subscribe to this mod's changes

integration-steward is an agent published in the GitHub repository Openly-Useful/operations-pulse (0 stars, last pushed 13d ago), licensed MIT. It adds 25 tokens to every session and 159 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories