菜单
Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action
基于 SOC 职业分类
One-command drift detection. Composes audit-list + oia-audit + audit-trend into a single primitive — finds the most recent audit in `metaharness-audit` namespace, runs a fresh audit against the current repo, diffs them via ADR-152 §3.1 similarity, and alerts when structural distance crosses `--threshold`. Iter 53 of ADR-150 deep integration.
ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall score in [0,1] plus per-component breakdown (cosine over 9 numerics, categorical agreement over 4 enums, jaccard over agent_topology). Unblocks ADR-151 §3.2 Recommender, §3.3 Drift Detection, §3.5 Plugin Compat. Pure-TS, no `@metaharness/*` dep — preserves ADR-150's four architectural constraints.
Composite Phase-2 audit worker (ADR-150). Bundles harness oia-manifest + threat-model + mcp-scan into one timestamped audit record stored in the `metaharness-audit` memory namespace. Designed for cron-scheduled drift detection.
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.
| name | browser-record |
| description | Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action |
| argument-hint | <url-or-task> [--with-dom] [--viewport WxH] |
| allowed-tools | mcp__claude-flow__browser_open mcp__claude-flow__browser_close mcp__claude-flow__browser_session-list mcp__claude-flow__browser_screenshot mcp__claude-flow__browser_snapshot mcp__claude-flow__browser_wait mcp__claude-flow__aidefence_has_pii mcp__claude-flow__aidefence_scan Bash Read Write |
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).
browser-extract, browser-form-fill, browser-test) will compose.SID="$(date +%Y%m%d-%H%M%S)-${TASK_SLUG:-record}"
npx -y ruvector@0.2.25 rvf create "$SID.rvf" --dimension 384
npx -y ruvector@0.2.25 hooks trajectory-begin --session-id "$SID" --task "$1"
mcp__claude-flow__browser_open with the URL.browser_snapshot for the accessibility tree, browser_screenshot for a baseline image.npx -y ruvector@0.2.25 hooks trajectory-step \
--session-id "$SID" --action click --args '{"selector":"#login"}' --result ok
npx -y ruvector@0.2.25 hooks trajectory-end --session-id "$SID" --verdict pass
npx -y ruvector@0.2.25 rvf compact "$SID.rvf"
browser-sessions:
npx -y @claude-flow/cli@latest memory store --namespace browser-sessions \
--key "$SID" --value "{rvf_id:$SID,host:...,task:...,verdict:pass}"
browser_session_record MCP tool ships (ADR-0001 §7), this skill drives the lifecycle from inside its own bash steps. Do not call mcp__claude-flow__browser_open directly without these wrappers.<YYYYMMDD-HHMMSS>-<task-slug>. Downstream /ruflo-browser ls parses this.--with-dom is expensive (full HTML dump per nav). Off by default.browser-record is a primitive; redaction is the responsibility of skills that read content (browser-extract, browser-test).