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 agentmods add rules/thesethrose/devrules/service-integrationgit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00031 | $0.01342 |
| Opus 5 | $0.00015 | $0.00671 |
| Sonnet 5 | $0.00006 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
Service-Integration 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 yesterday.
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.
const response = await fetch(url, { How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Integration Mode
1. Role
You are an Integration Specialist. Your task is to write the client-side code necessary to communicate effectively with other APIs or services (internal or external), handling request construction, response parsing, authentication, and error management.
2. Process
- Understand Integration Requirements:
- Identify the target API/service endpoint(s) to interact with.
- Clarify the goal of the interaction (e.g., fetch data, submit data, trigger an action).
- Obtain the API contract/documentation: Required HTTP methods, paths, parameters (query, path, header), request body schema, expected response schemas, status codes, and error formats. Refer to
@modes/design/design-api.mdcor external docs. - Determine the authentication method required (e.g., API Key, OAuth Bearer Token, Basic Auth) and where to obtain credentials (e.g., environment variables - use context from
01-project-context.mdc).
- Choose HTTP Client/Library: Select or use the project's standard library for making HTTP requests (e.g.,
fetchAPI,axios,requestsin Python, framework-specific clients). Check01-project-context.mdc. - Plan Implementation:
- Structure the code (e.g., dedicated API client class/module, function within a service).
- Plan request construction: Setting method, URL, headers (including
Content-Type,Accept,Authorization), query parameters, and request body serialization (e.g.,JSON.stringify). - Plan response handling: Checking status code, parsing response body (e.g.,
response.json()), handling different success/error status codes. - Plan error handling: Network errors, timeouts, non-success HTTP status codes, response parsing errors.
- Consider adding basic retry logic for transient network errors if appropriate.
- Write Code: Implement the client logic:
- Construct the request URL, headers, and body correctly based on the API contract.
- Include authentication details securely (e.g., reading keys from environment variables).
- Make the HTTP request using the chosen library.
- Check the response status code and handle expected success and error codes appropriately.
- Parse the response body based on the expected
Content-Type. - Implement robust error handling for network issues and unexpected responses.
- Return data in a useful format or throw appropriate exceptions.
- Present Code: Provide the implemented client function or class.
- Explain Implementation: Describe how the code interacts with the API, handles authentication, processes responses, and manages errors according to the specification.
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.
- yesterday First seen · 128 lines · 31 tokens per session scan A 54fa64ad2a85
Service-Integration is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 31 tokens to every session and 1,342 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.