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 celigo/ai --skill configuring-connectionsgit clone --depth 1 https://github.com/celigo/aiWrote 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/celigo/ai/configuring-connections)<a href="https://agentmods.dev/skills/celigo/ai/configuring-connections"><img src="https://agentmods.dev/badge/skills/celigo/ai/configuring-connections.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00050 | $0.08439 |
| Opus 5 | $0.00025 | $0.04220 |
| Sonnet 5 | $0.00010 | $0.01688 |
| Haiku 4.5 | $0.00005 | $0.00844 |
Grade A, and why
configuring-connections 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuring Connections
A connection is a credential and configuration object that lets Celigo communicate with an external system. Every export and import references a connection via _connectionId. Connections must be created before the resources that use them.
Concerns when configuring a connection:
- Authentication -- choosing the right auth method (OAuth, token, basic, key-pair, certificate, etc.) and providing the correct credentials
- Concurrency -- how many parallel requests Celigo can make to the target system (
concurrencyLevel). Can be shared across connections via_borrowConcurrencyFromConnectionId - Health monitoring -- ping configuration to verify connectivity and detect credential expiration (
offlinestatus) - Pre-built connectors -- HTTP connectors and trading partner connectors provide pre-configured auth, base URLs, and endpoint definitions for 550+ applications
- Debug logging -- temporary debug mode to capture raw request/response data for troubleshooting
- iClients -- reusable OAuth credential stores (client ID/secret, scopes, token endpoints) shared across connections. See iClients section below.
Used across flows, APIs, and tools.
Connection Types
| Target System | type |
Schema | Notes |
|---|---|---|---|
| REST/GraphQL API (with connector) | http |
http.yml | formType: "assistant", set _httpConnectorId |
| REST/GraphQL API (manual) | http |
http.yml | Three form types: assistant, http, graph_ql |
| NetSuite ERP | netsuite |
netsuite.yml | Use token-auto for new connections |
| Salesforce CRM | salesforce |
salesforce.yml | Use packagedOAuth: true for new connections |
| SQL Server, MySQL, Postgres, Oracle | rdbms |
rdbms.yml | |
| Snowflake, BigQuery, Redshift | rdbms |
rdbms.yml | Check sub-type in schema |
| Active Directory, Databricks, DB2 | jdbc |
jdbc.yml | |
| MongoDB/Atlas | mongodb |
mongodb.yml | |
| DynamoDB | dynamodb |
dynamodb.yml | |
| FTP/SFTP/FTPS server | ftp |
ftp.yml | Optional PGP encryption |
| Amazon S3 | s3 |
s3.yml | |
| Local filesystem | filesystem |
filesystem.yml | Requires agent via _agentId |
| AS2 EDI partner | as2 |
as2.yml | |
| Celigo VAN (EDI hub) | van |
van.yml | |
| AI tool server (MCP) | mcp |
mcp.yml | |
| Stack-deployed connector | wrapper |
wrapper.yml | |
| Legacy REST (do not use) | rest |
rest.yml | Use http instead |
What ships with it
27 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.
- references/iclient-schemas/base.yml 207 KB
- references/iclient-schemas/ebay.yml 1.1 KB
- references/iclient-schemas/netsuite.yml 723 B
- references/iclient-schemas/oauth2.yml 6.6 KB
- references/iclient-schemas/request.yml 587 B
- references/iclient-schemas/response.yml 567 B
- references/iclient-schemas/salesforce.yml 1.0 KB
- references/schemas/as2.yml 27 KB
- references/schemas/dynamodb.yml 3.3 KB
- references/schemas/filesystem.yml 2.8 KB
- references/schemas/ftp.yml 11 KB
- references/schemas/http.yml 43 KB
- references/schemas/jdbc.yml 11 KB
- references/schemas/jwt.yml 5.6 KB
- references/schemas/mcp.yml 7.5 KB
- references/schemas/mongodb.yml 5.3 KB
- references/schemas/netsuite.yml 11 KB
- references/schemas/oauth.yml 11 KB
- references/schemas/rdbms.yml 27 KB
- references/schemas/request.yml 13 KB
- references/schemas/response.yml 6.8 KB
- references/schemas/rest.yml 14 KB
- references/schemas/s3.yml 4.6 KB
- references/schemas/salesforce.yml 7.4 KB
- references/schemas/ssl.yml 1.9 KB
- references/schemas/van.yml 3.1 KB
- references/schemas/wrapper.yml 7.2 KB
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.
- 7d ago First seen · 495 lines · 50 tokens per session scan A a605b06553a9
configuring-connections is a skill published in the GitHub repository celigo/ai (3 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 8,439 once invoked, about $0.0003 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.
Other skills, from other repositories
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
developing-genkit-tooling
Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.