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.
npx skills add steerlabs/opensteer --skill integrationsgit clone --depth 1 https://github.com/steerlabs/opensteerWrote 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/skills/steerlabs/opensteer/integrations)<a href="https://agentmods.dev/skills/steerlabs/opensteer/integrations"><img src="https://agentmods.dev/badge/skills/steerlabs/opensteer/integrations/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/skills/steerlabs/opensteer/integrations"><img src="https://agentmods.dev/badge/skills/steerlabs/opensteer/integrations.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 | $0.00020 | $0.00371 |
| Opus 5.5 | $0.00008 | $0.00148 |
| Sonnet 5.5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
integrations 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 today.
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.
What it actually says
Opensteer Integrations
Use a fitting integration for service account and API work, including built-in connectors, remote MCP servers, proposed APIs and Agent Plugins. Find an operation that meets the goal, request any missing access from the person, and verify the result on the intended account.
Select accounts by connectionId, never display name. Search shows each operation's input, so call it directly with its name and the connectionId as account. The Host checks the current account and grant at execution.
Credentials belong in the Request UI. Except for SMS/email codes for a sign-in the person asked for (see boundaries), never collect or retrieve service secrets yourself, and never bypass denied access with another account or transport. Mac apps and Android phones use app() and phone() in the computer tool (opensteer:computer-use), never with integration_call.
Use integration_manage to list, disconnect, uninstall or revoke grants directly within
full-access and reach. channel_manage lists/revokes bindings or pauses/resumes existing
connections. These tools cannot create accounts, enter credentials or grant access.
Read only the reference needed for the work:
- Discovery when finding operations or interpreting readiness and paging.
- Operations when an operation needs more detail than search shows, or repairing a schema or account error.
- Requests when connecting, installing or requesting access.
- Proposals when the catalog has no fitting integration.
- Boundaries when handling credentials, computer-hosted services or Trigger access.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed d45bdefa4eb9
- yesterday Changed · +4 lines · -7 tokens per session 4a495fadcf9e
- 2d ago First seen · 21 lines · 27 tokens per session scan A 18f5506e74f3
integrations is a skill published in the GitHub repository steerlabs/opensteer (204 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 371 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 2026-11-04.
integrations compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| integrationssteerlabs/opensteer | Skill | 204 | today | MIT | A | 20 | Codex |
| n8n-docs-assistantn8n-io/n8n | Skill | 210k | yesterday | none | A | 71 | Claude Code, Codex |
| testingTeam-Commonly/commonly | Skill | 1.4k | yesterday | Apache-2.0 | A | 31 | Claude Code, Codex |
| webappkortix-ai/suna | Skill | 20k | 4d ago | none | A | 28 | Claude Code, Codex |
| write-script-graphqlwindmill-labs/windmill | Skill | 18k | yesterday | none | A | 14 | Claude Code, Codex |
| accounted-apierp-mafia/accounted | Skill | 461 | 3d ago | none | A | 123 | Claude Code, Codex |
| weave-api-callingTyox-all/Weave_Protocol | Skill | 1 | 2d ago | Apache-2.0 | A | 36 | Claude Code, Codex |