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.
git clone --depth 1 https://github.com/EvilFreelancer/openapi-to-cliWrote 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/rules/evilfreelancer/openapi-to-cli/workflow)<a href="https://agentmods.dev/rules/evilfreelancer/openapi-to-cli/workflow"><img src="https://agentmods.dev/badge/rules/evilfreelancer/openapi-to-cli/workflow/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/rules/evilfreelancer/openapi-to-cli/workflow"><img src="https://agentmods.dev/badge/rules/evilfreelancer/openapi-to-cli/workflow.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 | $0.01566 | $0.01566 |
| Opus 5.5 | $0.00626 | $0.00626 |
| Sonnet 5.5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
workflow 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow (TDD, layered, docs-aware)
This file is alwaysApply: true, so it loads in every Cursor session (same priority as the top-level project rules).
openapi-to-cli (ocli) is a TypeScript CLI that turns OpenAPI/Swagger specs into runtime commands. The user-facing surface is the ocli binary, .ocli/ config dir, and profiles.ini. Tests live next to source in tests/ and run with Jest. Behavior is specified by tests; the README documents the public CLI contract.
New features (TDD)
When the user asks for a new feature (words like "feature", "add", "implement", "фича", "добавить"), follow this order. Do not skip steps.
- Plan: outline the steps for the change (modules to touch, tests to add). Use a task list if it spans more than 2-3 steps.
- Failing test first: add or extend a test in
tests/<module>.test.ts. The test must describe the new behavior indescribe/itand fail for the right reason. - Confirm red: run only that test:
npx jest tests/<module>.test.ts -t "<title>". Confirm it fails as expected. - Implement: write the minimum code in
src/that makes the test pass. Follow @architecture.mdc and @code-style.mdc. When adding new classes, follow @implementation-order.mdc - lower layer first. - Confirm green: re-run the same test; it must pass.
- Full suite:
npm test. All tests must be green. Fix regressions before moving on. - Build check:
npm run buildto confirmtscis clean (no type errors). - Docs: update
README.mdwhenever any of the following change: CLI flags, command names, profile fields,.ocli/layout, BM25 search behavior, supported OpenAPI/Swagger features, authentication and header handling (which requests carry profile credentials and custom headers, and to which hosts), spec loading and caching (accepted sources,$refresolution, when the cache is refreshed), or the benchmark numbers. A change counts even when it adds no flag: if a user can observe the difference (a spec behind auth now loads, credentials reach a host they did not reach before), document it. If you changed observable CLI output (--help, error messages, exit codes), update the relevant section of the README. Theexamples/skill-ocli-api.mdandskills/ocli-api/SKILL.mdmust stay aligned with the documented agent workflow. - Report: brief summary of files touched, tests added, suite result.
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.
- 1mo ago Changed · +7 lines · +331 tokens per session 68a4f7d7d406
- 1mo ago First seen · 75 lines · 1,235 tokens per session scan A 5393e1231c27
workflow is a cursor rule published in the GitHub repository EvilFreelancer/openapi-to-cli (265 stars, last pushed 24d ago), licensed MIT. It adds 1,566 tokens to every session, about $0.0063 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 2026-08-30.
Other cursor rules, from other repositories
typescript-coding-rule
It allows a subset of JSDoc tags. Most tags must occupy their own line, with the tag at the beginning of the line.
deno
You MUST import @std dependencies from jsr You MUST use latest versions of libraries when adding imports You must use type keyword when importing types.
chassis
Chassis conventions — decorator-driven Express 5 + TypeScript.
typescript-standards
// Good: Typed error handling function loadConfig(): Config { try { // ... loading logic } catch (error) { if (error instanceof yaml.YAMLException) { throw new Error(Invalid YAML in configuration file: ${error.message}); } throw error; } }.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.