Browser Replay
Testing & Qualitybrowser-replayBrowser Replay is an Agent Skill for testing & quality published in the ruvnet/ruflo repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/ruvnet/ruflo/blob/HEAD/plugins/ruflo-browser/skills/browser-replay/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/browser-replay, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Browser Replay
Re-drive a recorded session trajectory. Used for regression testing, deterministic re-runs, and as the verification path that browser-record plus browser-selectors actually produces something replayable.
This skill is the load-bearing assumption of the v0.2.0 architecture. ADR-0001 Verification §4 requires ≥80% replay success across 10 distinct sites of varying drift profiles before the proposal moves from
Proposed→Accepted. If you find replay unreliable, capture the failure modes infindings.mdand report them up the ADR.
When to use
- Regression-testing a UI flow after a deploy.
- Reproducing a bug captured in a prior session.
- Comparing two runs of the same flow for
browser-screenshot-diff. - Forking a session (
/ruflo-browser fork) and replaying the parent before mutating.
Steps
- Locate the source session:
npx -y [email protected] rvf status <session-id>.rvf - Load the trajectory:
Each line isRead .../trajectory.ndjson{ts, action, args, selector, result}. - Open a fresh browser via
mcp__claude-flow__browser_open(target URL = original or--urloverride). - For each trajectory step, dispatch the matching MCP tool (
browser_click,browser_fill,browser_eval, etc.) with the recorded args. - On selector miss, do not fail immediately — query the
browser-selectorsnamespace for an embedding-similar selector for the same<host>:<intent>and retry once:npx -y @claude-flow/cli@latest memory search --namespace browser-selectors \ --query "<host> <intent>" --limit 5 - Record a new trajectory for the replay run (allocate a fresh RVF container, lineage-tracked via
rvf derive). - Verdict: tally matched-step / total-step ratio. Default tolerance threshold is 0.85 (configurable via
--tolerance). Verdict goes intofindings.md.
Caveats
- Browserbase explicitly does not offer replay (rrweb session replay was deprecated). We're betting on selector-embedding recovery; expect noise on heavily drifted sites.
- Network nondeterminism (timing, content variation) can produce false-fail verdicts. Use
--mutateto inject expected variation or pin to a fixture. - For visual diff, chain into
browser-screenshot-diffagainst the parent session id. - If selector recovery requires more than one retry per step, log it. That's the signal that the site needs a re-record, not a replay.