recommend-connectors

recommend-connectors is a skill for Claude Code from rojim666/SztuCode. It costs 46 tokens per session (448 once invoked), scanned A, original, MIT.

A workflow for finding and recommending connectors to external apps, services, APIs, or MCP servers. A connector is a link that lets an assistant work with an outside system or its data.

In plain words
What is it for?
Use it when a task needs a third-party app, authorisation, API, MCP server, or external data source.
Why use it?
It helps identify a suitable connection when the available tools cannot access the required service. It only recommends connectors that match the task and are not already connected.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when a task needs a third-party app, authorisation, API, MCP server, or external data source.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rojim666/sztucode/recommend-connectors
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.

Any agent
npx skills add rojim666/SztuCode --skill recommend-connectors
Clone the repo
git clone --depth 1 https://github.com/rojim666/SztuCode

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 recommend-connectors

README.md
[![agentmods](https://agentmods.dev/badge/skills/rojim666/sztucode/recommend-connectors/github.svg)](https://agentmods.dev/skills/rojim666/sztucode/recommend-connectors)
Your own site
<a href="https://agentmods.dev/skills/rojim666/sztucode/recommend-connectors"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/recommend-connectors/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 recommend-connectors

Your own site · 80×15
<a href="https://agentmods.dev/skills/rojim666/sztucode/recommend-connectors"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/recommend-connectors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 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 $0.00046 $0.00448
Opus 5.5 $0.00018 $0.00179
Sonnet 5.5 $0.00009 $0.00090
Haiku 4.5 $0.00005 $0.00045

Measured 1mo ago against content hash d2a40c6d729b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

recommend-connectors 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 1mo 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.

packages/runtime-ts/prompts/Sztubuddy/skills/recommend-connectors/SKILL.md · 39 lines

What it actually says

Recommend Connectors

Use this Skill only when the current task directly requires an external service, authorization, or the user's third-party data and the available tools cannot complete it.

Workflow

  1. Call search_plugins with type set to connector. Put the user's request, verbatim or lightly paraphrased, in userIntent; add keywords only when useful.
  2. Keep only candidates that directly help with the current task and are still disconnected in the search results.
  3. Select at most three candidates. Every plugin ID must exactly match an id returned by this search_plugins call; never guess or rewrite an ID.
  4. Call suggest_plugin_install exactly once to render one Connector card. If recommending multiple candidates, include all of them in this single call:
{
  "type": "connector",
  "contextLabel": "For your code repositories",
  "pluginId1": "github",
  "pluginId2": "gitlab"
}

Rules

  • Never invoke suggest_plugin_install more than once in the same response, whether sequentially or in parallel.
  • A single suggest_plugin_install call can recommend one to three candidates by using pluginId1, pluginId2, and pluginId3.
  • Never install, connect, or authorize a Connector directly; every action must be initiated by the user from the card.
  • Do not replace the suggest_plugin_install card with a text list.
  • If the search returns no relevant results, silently continue the original task without describing the internal search process.
  • After the user skips, times out, or cancels, do not recommend the same candidates again in the same response.
  • Never use web search to find Plugins; search_plugins is the only source for candidates.
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. 1mo ago First seen · 39 lines · 46 tokens per session scan A d2a40c6d729b

Subscribe to this mod's changes

recommend-connectors is a skill published in the GitHub repository rojim666/SztuCode (110 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 448 once invoked, about $0.0002 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 2026-09-12.

Related

Other skills, from other repositories

codex-delegate

Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" …

amElnagdy/delegate-skills · 155 tokens

commandcode-delegate

Delegate a coding task to the Command Code CLI (cmd) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code…

amElnagdy/delegate-skills · 123 tokens

claude-delegate

Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…

amElnagdy/delegate-skills · 117 tokens

copilot-delegate

Delegate a coding task to the GitHub Copilot CLI (copilot) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Copilot - phrasings like "have Copilot implement X", "delegate this to copilot", "run it through Copilot CLI", or "use…

amElnagdy/delegate-skills · 129 tokens

cursor-delegate

Delegate a coding task to the Cursor Agent CLI (cursor-agent) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use…

amElnagdy/delegate-skills · 120 tokens

cline-delegate

Delegate a coding task to the Cline coding agent CLI (cline) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Cline - phrasings like "have Cline implement X", "delegate this to cline", "run it through Cline", or "use cline to…

amElnagdy/delegate-skills · 126 tokens