Browser Operator
This is a Hermes-native browser-operator workflow skill.
Why This Exists
browser-operator exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
Do Not Use When
- The request is already handled by a narrower explicit skill with stronger evidence.
- The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
- The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
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/payment/purchase/destruction/scraping/export; observed traces only.
- 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.
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.
Workflow Lane
- Current lane: Automation and status (
achievements, workspace-audit, production-audit, automation-blueprint, github-event-ops, github-issue-intake, buzz, agent-board, +35 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:
omh-routing/references/skill-common-rail.md.
Use When
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.
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: omh-routing/references/skill-common-rail.md. Load it when applicable; otherwise name an unavailable capability.
1---
2name: "omh-browser"
3description: "[omh] Policy overlay for browser tasks - add auth, confirmation, and observed-trace gates after preferring the native browser for ordinary URL, click, login, and form actions. Use when the user says: browser-operator, browser operator, browser task, browser operation, browser automation, browser session, webpage operation, web page operation."
4metadata:
5 hermes:
6 tags: [workflow, oh-my-hermes, browser]
7 category: browser
8 phase: browser-task
9 role: guide
10 quality_tier: workflow-surface-gated
11---
12
13# Browser Operator
14
15This is a Hermes-native `browser-operator` workflow skill.
16
17## Why This Exists
18
19`browser-operator` exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
20
21## Do Not Use When
22
23- The request is already handled by a narrower explicit skill with stronger evidence.
24- The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
25- The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
26
27## Examples
28
29Good example:
30
31- Prompt: browser-operator open the staging checkout URL, click login, fill the form, and capture blockers.
32- Expected behavior: Produce `prepare_browser_operator_card` with required context, wrapper actions, and not-evidence boundaries.
33- Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.
34
35Bad example:
36
37- Prompt: browser-operator use saved credentials and submit the production payment form without confirmation.
38- Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
39- Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.
40
41## Completion Checklist
42
43- Specify URL, allowed/prohibited actions, auth boundary, stop condition.
44- Gate credentials/login/payment/purchase/destruction/scraping/export; observed traces only.
45- Host request admission (not enablement/adapter presence) gates schemas/context/callbacks/writes. Refuse foreign/stale/expired/released/ambiguous targets; no index fallback.
46- omh_browser blocks native browser_*; inert by default. Opted-in effects need exact approval: docs/BROWSER-EFFECTS.md.
47
48## Recovery Notes
49
50- Missing target/confirmation: ask; visual correctness: visual-qa.
51- Refresh stale state once; never replay unknown work. Reuse acquisitions; only owner adapter/version reaps. Release needs observed cleanup, not mutation approval.
52- Host receipt BLOCK: production click/submit, retry after auth/4xx/assertion/mutation failure, or over two transient read-only retries.
53- 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.
54- Trace drift: `promotion status` unlinks only managed SKILL.md, keeps generations/receipts; no autoheal/watch/global fallback.
55
56## Workflow Lane
57
58- Current lane: **Automation and status** (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `github-issue-intake`, `buzz`, `agent-board`, `+35 more`) - schedules, status, health, and ops review.
59- If intent belongs to another lane, hand back to `oh-my-hermes` or name the adjacent workflow.
60- Shared product, routing, compatibility, and evidence rules: `omh-routing/references/skill-common-rail.md`.
61
62## Use When
63
64Use 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.
65
66 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`
67
68## Catalog Metadata
69
70Category: `browser`
71Phase: `browser-task`
72Hermes role: `guide`
73Quality tier: `workflow-surface-gated`
74Reasoning demand: `standard`
75
76Quality bar:
77
78- Name the user-facing workflow objective, required context, next action, and stop condition.
79- Separate prepared guidance from observed platform, runtime, connector, file, memory, or delivery evidence.
80- Expose missing tools, credentials, targets, or observations as user-visible gaps.
81
82Handoff policy:
83
84Keep 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.
85
86Required inputs:
87
88- user request
89- target context
90- delivery or status expectation
91- known missing evidence
92
93Expected outputs:
94
95- browser_task_card/v1
96- browser_interaction_scope/v1
97- browser_auth_boundary/v1
98- browser_observation_manifest/v1 when observed
99- browser_confirmation_gate/v1 when destructive
100- browser_adapter_capabilities/v1 when acquired
101- browser_session_lease/v1 when acquired
102- browser_page_state/v1 when observed
103- next action
104- prepared-vs-observed boundary
105
106Artifact expectations:
107
108- browser_task_card/v1 metadata only
109- browser_interaction_scope/v1: URL, allowed/prohibited actions, stop condition
110- browser_auth_boundary/v1: supplied/missing/prohibited credentials
111- browser_observation_manifest/v1: observed screenshots/DOM notes/console/network/click traces only
112- Leases: docs/BROWSER-ADAPTER.md; owner/adapter/version/task scope, cached capabilities, digest-only state, exact revision handles.
113- browser_skill_promotion/v1: `omh web-qa promotion diff`, `approve` its exact digest, then `promote` one receipt; SKILL.md alone commits visibility
114
115Safety rules:
116
117- Cards prove no execution. Gate credentials and destructive actions; require observed traces.
118- Do not claim connector, gateway, runtime, file generation, memory mutation, or host automation evidence from prepared guidance.
119
120## Runtime Evidence
121
122Preferred harness for this skill: `browser-operator`.
123
124```sh
125omh runtime record --skill browser-operator --harness browser-operator --status started
126```
127
128Record observed delegation results; otherwise return `not_available` or `not_observed`.
129Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
130- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
131Preserve workflow intent and stop conditions; verify before claiming completion.
132
133Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
134
135Shared product, compatibility, topology, memory, harness, and execution rules: `omh-routing/references/skill-common-rail.md`. Load it when applicable; otherwise name an unavailable capability.