agentmods.dev

source-connector

source-connector is a skill for Claude Code from AGoldian/claudenv. It costs 142 tokens per session (1,526 once invoked), scanned A, original, MIT.

A guided way to connect a coding agent to a data source that has no ready-made connection, such as an internal database, company wiki, reporting tool, or custom web API.

In plain words
What is it for?
Use it to add a source, connect to internal or custom data systems, generate the connector code, and retain its settings and origin for later use.
Why use it?
It turns an otherwise unsupported source into a reusable connector while keeping credentials in a local environment file and separating workspaces.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

not rated 10repo 5mo ago A scan 142 tokens original MIT

Good fit Use it to add a source, connect to internal or custom data systems, generate the connector code, and retain its settings and origin for later use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agoldian/claudenv/source-connector
View source ↗ AGoldian/claudenv npmjs.com
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 AGoldian/claudenv --skill source-connector
Clone the repo
git clone --depth 1 https://github.com/AGoldian/claudenv

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 source-connector

README.md
[![agentmods](https://agentmods.dev/badge/skills/agoldian/claudenv/source-connector/github.svg)](https://agentmods.dev/skills/agoldian/claudenv/source-connector)
Your own site
<a href="https://agentmods.dev/skills/agoldian/claudenv/source-connector"><img src="https://agentmods.dev/badge/skills/agoldian/claudenv/source-connector/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 source-connector

Your own site · 80×15
<a href="https://agentmods.dev/skills/agoldian/claudenv/source-connector"><img src="https://agentmods.dev/badge/skills/agoldian/claudenv/source-connector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00142 $0.01526
Opus 5.5 $0.00057 $0.00610
Sonnet 5.5 $0.00028 $0.00305
Haiku 4.5 $0.00014 $0.00153

Measured 2mo ago against content hash 862bf5b085c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

source-connector scanned grade A 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(СУЗ - логин без домена; экранируй пароль через urllib `quote_plus`).
scaffold/global/.claude/skills/source-connector/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source connector

Создаёт коннектор к источнику данных без готового MCP: внутренний SQL/DWH, корпоративная вики, Redash, YouTrack, самописный REST. Опрашивает юзера, генерирует рабочий скрипт, кладёт секреты в .env.local, кэширует знание о коннекторе (параметры + provenance) в память АКТИВНОГО workspace.

Step 0 - Workspace resolution (FIRST, every time)

Память изолирована по пространствам (workspaces). Прежде чем что-либо писать:

  1. Определи активный workspace:
    • env CLAUDENV_WORKSPACE, иначе файл ~/.claudenv/active-workspace.
    • если есть claudenv CLI: claudenv workspace show.
  2. Если активного нет - предложи выбрать из ~/.claudenv/workspaces/ или создать новый. НИКОГДА не подтягивай и не пиши в «глобальную» память доступы/коннекторы.
  3. Все записи коннектора пиши ТОЛЬКО в активный workspace: ~/.claudenv/workspaces/<id>/memories/connectors/.
  4. НИКОГДА не читай чужие workspaces - это барьер от ликов между компаниями.

Security invariants (нарушать нельзя)

  • Секреты (пароли, токены, ключи) - только в <project>/.env.local и только значениями там. Убедись, что .env.local есть в .gitignore (добавь, если нет).
  • В память коннектора - НИКОГДА значения секретов. Только secret_refs - имена переменных из .env.local.
  • Не эхай секреты в вывод/логи/коммиты.
  • Память активного workspace изолирована: не смешивай контекст разных компаний.

Trigger criteria

Триггерь, если юзеру нужно регулярно/программно ходить в источник:

  • БД (MSSQL/Postgres/ClickHouse), DWH за VPN
  • корпоративная вики (Confluence), Redash, YouTrack, Grafana
  • самописный REST/GraphQL API

НЕ триггерь:

  • если для источника есть MCP-сервер - предложи MCP (см. ниже)
  • разовое чтение локального файла
  • источник уже подключён (тогда это обновление, см. Step 6)

Step 1 - MCP vs connector

Сначала проверь, нет ли готового MCP для источника (claudenv умеет настраивать MCP в .mcp.json). Если есть - предложи MCP-путь. Коннектор - для источников БЕЗ MCP.

Read the full file on GitHub · 129 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. 2mo ago First seen · 129 lines · 142 tokens per session scan A 862bf5b085c6

Subscribe to this mod's changes

source-connector is a skill published in the GitHub repository AGoldian/claudenv (10 stars, last pushed 5mo ago), licensed MIT. It adds 142 tokens to every session and 1,526 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIsClaude Codeai-agentsantropicclaudedevtools
Related

source-connector compared with skills from other repositories

source-connector next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
source-connectorAGoldian/claudenvSkill105mo agoMITA142Claude Code
devtools-event-clientTanStack/devtoolsSkill514yesterdayMITA79Claude Code, Codex
manage-mcpnuxt-modules/mcp-toolkitSkill1822d agoMITB50Claude Code, Codex
revergreekr4/rever-browserSkill55yesterdayMITA82Claude Code, Codex
aws-serverless-patternsseandkendall/kiro-configSkill82d agoApache-2.0A43Claude Code, Codex
amazon-location-serviceseandkendall/kiro-configSkill82d agoApache-2.0A20Claude Code, Codex
cognito-email-migrationseandkendall/kiro-configSkill82d agoApache-2.0A57Claude Code, Codex