Cline — `.clinerules/` convention — zero setup.

How it plugs in

Cline, the VS Code / terminal AI coder, picks up `.clinerules/peepshow.md` automatically. The rule gives Cline the CLI signature, the `--emit` output schema, and guidance on when to call peepshow.

Install

git clone --depth 1 https://github.com/t0mtaylor/peepshow.git
# Cline reads .clinerules/ — no extra setup.

Files involved

• .clinerules/peepshow.md Rule: when to call peepshow and how to parse its output.

In practice

user: there's a bug in recording.mp4, can you see it?
cline: (runs peepshow → reads frames → points at offending frame)

All 95 sinks still work

The CLI is the same across agents — which means every sink documented under /sinks is available here. Auto-sinks fire regardless of which agent invoked peepshow.

Report + LLM analysis loop

Every run also writes a self-contained report.html + manifest.json next to the frames (see the Report page). When Cline consumes the frames, the analysis flows back into the report so whoever opens it next sees the model's understanding without re-running the prompt.

echo '{"summary":"<your summary>","provider":"cline"}' \
  | peepshow report annotate "<outputDir>"

The annotate instruction is wired into the Cline integration — the agent runs it after reading the frames + transcript. Report walkthrough →