Extract ACDL from a Repo

Point the extractor at any agent codebase and get back the ACDL specification of how it assembles context — with a line-by-line evidence table.

HTTPS, SSH, or just owner/repo. GitHub, GitLab, Bitbucket, or any git host.

Try:

What the extractor does

Reverse-engineers the message array your agent builds before every model call

Reads source, not docs

It works from the code that actually assembles the prompt. READMEs describe intent; the message array is the ground truth.

Never runs your code

Read-only file access, scoped to the checkout. Nothing in the target is executed or modified — the deliverables land in a separate output directory.

Cites its evidence

Every line of the emitted spec is traced to a file and line number in the report, so you can check the extraction instead of trusting it.

Takes a few minutes

A real extraction is a long agentic run over the whole codebase — minutes of wall time and a few dollars of tokens, not an instant answer.

Then what?

The spec is a normal .acdl file — the rest of the toolchain takes it from there