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 withoneai/one-agent-plugin --skill integration-codegit clone --depth 1 https://github.com/withoneai/one-agent-pluginWrote 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/withoneai/one-agent-plugin/integration-code)<a href="https://agentmods.dev/skills/withoneai/one-agent-plugin/integration-code"><img src="https://agentmods.dev/badge/skills/withoneai/one-agent-plugin/integration-code/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/withoneai/one-agent-plugin/integration-code"><img src="https://agentmods.dev/badge/skills/withoneai/one-agent-plugin/integration-code.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 | $0.00086 | $0.01000 |
| Opus 5.5 | $0.00034 | $0.00400 |
| Sonnet 5.5 | $0.00017 | $0.00200 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
integration-code 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing integration code with real API schemas
Integration code fails on details a model cannot recall: the exact field name, whether a value goes in the body or the query string, which enum the API accepts this year. One's action documentation carries all of it, so look the API up rather than writing from memory.
This is what knowledge-only mode is for. In an editor, execute_one_action is removed, so you can read every API's real schema while writing code and cannot fire a live request against production data by accident.
Before you write the call
find_one_actionswith onerequestsentry per operation the feature needs, on any platforms: theplatformand anintentnaming the operation alone ("create a customer", "list orders since a date"). One call covers every API the feature touches.- Read each chosen action's documentation whole: required and optional parameters, types, enums, auth, the request shape, and the response shape. In knowledge-only mode it comes back whole, with how to call it from code; otherwise call
find_one_actionsagain withload: [{ "action_id": "...", "full": true }]for any document that came back as a digest. - Write the code from that schema. Field names, casing, nesting, and types come from the documentation, not from what the API probably looks like.
If you write a request body with a field the documentation does not list, you invented it. Go back and check.
Two ways to ship the call
Through One. Keep One in the runtime and call the action through it. The user's connection handles auth, so your code holds no per-platform tokens and no refresh logic. Good when the app already has One in it or when you are integrating several platforms.
Direct to the platform. Use One's documentation as a reference and write a normal HTTP client against the vendor's API. Good when the integration is one platform deep or the runtime cannot take another dependency. You then own OAuth, token refresh, and rotation.
Say which one you are doing and why, in a sentence, before you write the file. Do not mix them in the same module.
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.
- 11d ago First seen · 57 lines · 86 tokens per session scan A ffc5ab28f7e5
integration-code is a skill published in the GitHub repository withoneai/one-agent-plugin (1 stars, last pushed 12d ago), licensed MIT. It adds 86 tokens to every session and 1,000 once invoked, about $0.0003 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 2026-10-04.
Other skills, from other repositories
amazon-location-service
Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text…
amplify-workflow
Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync/DynamoDB including schema modeling, enum types, relationships, authorization rules), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock). Supports React, Next.js, Vue…
aws-lambda-durable-functions
Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with…
webhook-subscriptions
Webhook subscriptions: event-driven agent runs.
api-gateway
Build, manage, and operate APIs with Amazon API Gateway (REST, HTTP, and WebSocket). Triggers on phrases like: API Gateway, REST API, HTTP API, WebSocket API, custom domain, Lambda authorizer, usage plan, throttling, CORS, VPC link, private API. Also covers troubleshooting API Gateway errors (4xx, 5xx, timeout, CORS…
aws-lambda
Design, build, deploy, test, and debug serverless applications with AWS Lambda. Triggers on phrases like: Lambda function, event source, serverless application, API Gateway, EventBridge, Step Functions, serverless API, event-driven architecture, Lambda trigger. For deploying non-serverless apps to AWS, use…