Plenty of internal APIs have no spec, so every integration starts with guesswork and a tab full of trial requests. This extractor probes the live API and writes the document for you.
sonnet4 daysPythonOpenAIPostmanGitHub
Claude
74ROI
84Scale
$2.2k93Saved
ROI for
README.md
Why this subagent
Plenty of internal APIs have no spec, so every integration starts with guesswork and a tab full of trial requests. This extractor probes the live API and writes the document for you.
It infers parameters, response shapes, and status codes from real responses, assembles an OpenAPI 3.1 file, and lints it before committing. You get a working spec in a pull request, ready to review and feed into your client generators and docs.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Infer request parameters, response shapes, and status codes from the live responses.
pending
Assemble a valid OpenAPI 3.1 document and lint it against the spec.
pending
Commit the generated spec to the repo and open a pull request for review.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given an API base URL and sample calls, probe the endpoints and return a valid, linted OpenAPI 3.1 document describing paths, parameters, and response schemas.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.