with one click
browser-replay
Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift
Menu
Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift
Spawn nested sub-agents (agents that spawn sub-agents, up to depth=5) via Claude Code's native Task tool — for context-managed deep delegation
Author a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration script (agent/parallel/pipeline fan-out)
Run a workflow — drive an MCP workflow lifecycle (execute/pause/resume/cancel) or invoke + resume a native .claude/workflows/*.js orchestration via the Workflow tool
Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap
Diagnose why a GAIA question failed — extract trace, classify failure mode, and propose a fix
Walk through a complete GAIA benchmark→submit flow — from key resolution through HAL-compatible package generation
| name | browser-replay |
| description | Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift |
| argument-hint | <session-id> [--url <new-url>] [--mutate <json>] [--tolerance <0..1>] |
| allowed-tools | mcp__claude-flow__browser_open mcp__claude-flow__browser_close mcp__claude-flow__browser_click mcp__claude-flow__browser_fill mcp__claude-flow__browser_type mcp__claude-flow__browser_press mcp__claude-flow__browser_select mcp__claude-flow__browser_check mcp__claude-flow__browser_uncheck mcp__claude-flow__browser_hover mcp__claude-flow__browser_wait mcp__claude-flow__browser_screenshot mcp__claude-flow__browser_snapshot mcp__claude-flow__browser_eval Bash Read |
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.
browser-screenshot-diff./ruflo-browser fork) and replaying the parent before mutating.npx -y ruvector@0.2.25 rvf status <session-id>.rvf
Read .../trajectory.ndjson
Each line is {ts, action, args, selector, result}.mcp__claude-flow__browser_open (target URL = original or --url override).browser_click, browser_fill, browser_eval, etc.) with the recorded args.browser-selectors namespace 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
rvf derive).--tolerance). Verdict goes into findings.md.--mutate to inject expected variation or pin to a fixture.browser-screenshot-diff against the parent session id.