evidence: witness windsurf on a real run

[jothimani-rajendran]

windsurf's matrix row currently rests on third-party-install — the hooks.json schema as
shipped in 2026-08 — not on anyone watching the agent run. That is an honest label, and it is
also the gap this project exists to close: a capability nobody re-ran is a claim, not a
measurement.

A schema tells you what an agent will accept. It does not tell you what it does with a deny,
or what happens when the hook crashes. Those are the two things the matrix actually claims.

If you have windsurf installed, you can close this in about two minutes.

python3 tools/capture.py detect
python3 tools/capture.py install --agent windsurf
# ...use windsurf normally for a minute...
python3 tools/capture.py report
python3 tools/capture.py uninstall --agent windsurf

Then open an issue with the Evidence report template and paste the result.

Things worth knowing before you start, all covered in CONTRIBUTING.md:

• The capture probe always allows. It records and gets out of the way, so it cannot break
  a session.
• Payloads are reduced to shape before anything touches disk -- keys and types survive,
  values become markers like <str:41>.
• A result that contradicts the matrix is the most valuable thing you can send. We are not
  collecting confirmations. If your run says windsurf behaves differently from what we publish,
  that is a row we are getting wrong in public.
• A hook that never fires is still a finding -- it means the config path or format is wrong
  for your version, which is exactly what documentation does not tell you. Report it with the
  version.

No code required. Report the agent's version alongside the result.