Browser Operator

This is a Hermes-native browser-operator workflow skill.

Why This Exists

browser-operator exists because native browser tools act on a live page with no scope, sign-in boundary, or trace requirement of their own: it fixes the URL, allowed actions, and stop condition, sends sign-ins and saved cards to Hermes' credential vault so secrets never pass through chat, and counts only observed page evidence.

Do Not Use When

• An ordinary read of a public page with no sign-in, form, or purchase; use the native browser tools directly unless OMH's browser adapter bridge is enabled, which blocks them.
• The question is whether a page looks right at each viewport; use omh-visual-qa.
• A web lookup or a cited answer rather than an interaction with a page; use omh-web-research.
• A page step that moves money -- a checkout, a payment, a booking deposit, a top-up; use omh-spend-gate, which shows the pre-spend card and takes the person's typed yes even when Hermes prompts on its own.

Examples

Good example:

• Prompt: browser-operator open the staging checkout URL, click login, fill the form, and capture blockers.
• Expected behavior: Produce prepare_browser_operator_card with required context, wrapper actions, and not-evidence boundaries.
• Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.

Bad example:

• Prompt: browser-operator use saved credentials and submit the production payment form without confirmation.
• Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
• Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.

Completion Checklist

• Specify URL, allowed/prohibited actions, auth boundary, stop condition.
• Gate credentials/login/destruction/scraping/export; a payment or purchase step waits for omh-spend-gate's card and typed yes; observed traces only.
• With nobody to answer the confirmation (a scheduled job, a one-shot run, a webhook run), an irreversible or externally visible action is not run: it is handed to a person's turn and its confirmation is recorded as missing.
• Host request admission (not enablement/adapter presence) gates schemas/context/callbacks/writes. Refuse foreign/stale/expired/released/ambiguous targets; no index fallback.
• omh_browser blocks native browser_*; inert by default. Opted-in effects need exact approval: docs/BROWSER-EFFECTS.md.
• Sign-ins, one-time codes, and saved cards go through browser_vault when browser_vault is in your tool list or tool_search finds it (list first; fill for a saved login, card, or address; enter_code for a one-time code after the password; save_login when nothing is saved for the site, so the user types it into Hermes' masked prompt; Hermes asks the user before it fills a card and refuses that in a headless run, and that answer sits beside omh-spend-gate's typed yes, never in place of it): no password, card number, card security code, or one-time code is asked for, typed, or echoed in chat; record only its success and filled_fields, and never retry a payment_declined. Without it, the sign-in is the user's own step and a named gap.

Recovery Notes

• Missing target/confirmation: ask; visual correctness: visual-qa.
• Refresh stale state once; never replay unknown work. Reuse acquisitions; only owner adapter/version reaps. Release needs observed cleanup, not mutation approval.
• Host receipt BLOCK: production click/submit, retry after auth/4xx/assertion/mutation failure, or over two transient read-only retries.
• POSIX native agent-browser collector: cold-desktop anonymous read-only Chromium only; other engine/profile/fixture/locale/timezone: named blocker (unsupported_browser_engine_webkit), never substitution.
• Trace drift: promotion status unlinks only managed SKILL.md, keeps generations/receipts; no autoheal/watch/global fallback.
• With OMH's browser adapter bridge enabled (browser_adapter.enabled), OMH's own hook blocks every native browser_* tool, the credential vault included: report the vault as blocked by the bound omh_browser lifecycle and never fall back to credentials in chat.

Workflow Lane

• Current lane: Automation and status (achievements, workspace-audit, production-audit, live-incident-response, automation-blueprint, github-event-ops, github-issue-intake, buzz, +40 more) - schedules, status, health, and ops review.
• If intent belongs to another lane, hand back to oh-my-hermes or name the adjacent workflow.
• Shared product, routing, compatibility, and evidence rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md').

When to Use

Use when Hermes should prepare or supervise a browser/page interaction request such as opening a URL, clicking, logging in, filling forms, or capturing page blockers without claiming browser execution.

Strong routing signals: `browser-operator`, `browser operator`, `browser task`, `browser operation`, `browser automation`, `browser session`, `webpage operation`, `web page operation`, `open url`, `open the url`, `open page`, `open the page`, `visit url`, `visit page`, `navigate url`, `navigate page`, `click page`, `click this page`, `click button`, `click login`, `login page`, `fill form`, `fill the form`, `submit form`, `checkout url`, `capture blockers`, `page blockers`, `interactive page`, `browser trace`, `browser observation`, `playwright task`, `웹페이지`, `웹 페이지`, `브라우저`, `브라우저 작업`, `브라우저 조작`, `페이지 열고`, `url 열고`, `링크 열고`, `클릭`, `로그인`, `로그인 폼`, `폼 작성`, `폼 입력`, `캡처`, `막히는 부분`

Catalog Metadata

Category: browser Phase: browser-task Hermes role: guide Quality tier: workflow-surface-gated Reasoning demand: standard

Quality bar:

• Name the user-facing workflow objective, required context, next action, and stop condition.
• Separate prepared guidance from observed platform, runtime, connector, file, memory, or delivery evidence.
• Expose missing tools, credentials, targets, or observations as user-visible gaps.

Handoff policy:

Keep this as Hermes-facing orchestration guidance first. Prepare executor, connector, gateway, or host-runtime handoff only when the user accepts that next step and observed evidence can be recorded.

Required inputs:

• user request
• target context
• delivery or status expectation
• known missing evidence

Expected outputs:

• browser_task_card/v1
• browser_interaction_scope/v1
• browser_auth_boundary/v1
• browser_observation_manifest/v1 when observed
• browser_confirmation_gate/v1 when destructive
• browser_adapter_capabilities/v1 when acquired
• browser_session_lease/v1 when acquired
• browser_page_state/v1 when observed
• next action
• prepared-vs-observed boundary

Artifact expectations:

• browser_task_card/v1 metadata only
• browser_interaction_scope/v1: URL, allowed/prohibited actions, stop condition
• browser_auth_boundary/v1: supplied/missing/prohibited credentials
• browser_observation_manifest/v1: observed screenshots/DOM notes/console/network/click traces only
• Leases: docs/BROWSER-ADAPTER.md; owner/adapter/version/task scope, cached capabilities, digest-only state, exact revision handles.
• browser_skill_promotion/v1: omh web-qa promotion diff, approve its exact digest, then promote one receipt; SKILL.md alone commits visibility

Safety rules:

• Cards prove no execution. Gate credentials and destructive actions; require observed traces.
• Do not claim connector, gateway, runtime, file generation, memory mutation, or host automation evidence from prepared guidance.

Runtime Evidence

Preferred harness for this skill: browser-operator.

omh runtime record --skill browser-operator --harness browser-operator --status started

Record observed delegation results; otherwise return not_available or not_observed. Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.

• Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes. Preserve workflow intent and stop conditions; verify before claiming completion. Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only; OMH's record terms (surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in records and tool calls, never in the sentence the user reads unless they ask about one; and when a stop condition or a decision the user owns ends the turn, offer the next action as a question rather than declaring what will not be done.

Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.

Shared product, compatibility, topology, memory, harness, and execution rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md'). Load it when applicable; otherwise name an unavailable capability.