mcpField
B
browser-record

browser-record

github.com/ruvnetAgent workflows80.0k718 installsUpdated today
Repository

About browser-record

browser-record is a browser-session skill for people running interactive browser tasks that need a trace for replay or analysis. It creates and indexes a session while recording its actions and state.

Key features

  1. 01Create named browser sessions
  2. 02Capture accessibility and screenshot snapshots
  3. 03Record interaction trajectories
  4. 04Compact and index session artifacts

Use cases

  1. 01Preserve a site exploration for later review
  2. 02Set up sessions for downstream browser skills

MCP support

It opens the browser through an MCP browser tool and binds session actions to a recorded trajectory.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill browser-record

After installing, type/browser-recordin Claude Code to confirm it loaded.

Details

From the project README

Browser Record

Primitive on which every other browser skill composes. Opens a named browser session, allocates an RVF container for it, and binds every action to a ruvector trajectory step. You do not run a browser session in this plugin without invoking this skill (or one that wraps it).

When to use

  • Starting any browser interaction that is not a one-off throwaway probe.
  • Exploring a site interactively while preserving the trace for later replay or analysis.
  • Establishing a reusable session that downstream skills (browser-extract, browser-form-fill, browser-test) will compose.

Steps

  1. Allocate session id and RVF container: 
    SID="$(date +%Y%m%d-%H%M%S)-${TASK_SLUG:-record}"
npx -y [email protected] rvf create "$SID.rvf" --dimension 384
npx -y [email protected] hooks trajectory-begin --session-id "$SID" --task "$1"
  2. Open the browser via mcp__plugin_ruflo-core_ruflo__browser_open with the URL.
  3. Snapshot the initial state: browser_snapshot for the accessibility tree, browser_screenshot for a baseline image.
  4. For each interaction, record a trajectory step before and after: 
    npx -y [email protected] hooks trajectory-step \
  --session-id "$SID" --action click --args '{"selector":"#login"}' --result ok
  5. End cleanly: 
    npx -y [email protected] hooks trajectory-end --session-id "$SID" --verdict pass
npx -y [email protected] rvf compact "$SID.rvf"
  6. Index in AgentDB under browser-sessions: 
    npx -y @claude-flow/cli@latest memory store --namespace browser-sessions \
  --key "$SID" --value "{rvf_id:$SID,host:...,task:...,verdict:pass}"

Caveats

  • Until the browser_session_record MCP tool ships (ADR-0001 §7), this skill drives the lifecycle from inside its own bash steps. Do not call mcp__plugin_ruflo-core_ruflo__browser_open directly without these wrappers.
  • The session id format is fixed: <YYYYMMDD-HHMMSS>-<task-slug>. Downstream /ruflo-browser ls parses this.
  • --with-dom is expensive (full HTML dump per nav). Off by default.
  • AIDefence gates apply at extraction time, not at navigation time. browser-record is a primitive; redaction is the responsibility of skills that read content (browser-extract, browser-test).

Comments

Markdown supported