@omniaibot/win-x64 1.6.6 → 1.6.7

package/bin/omnibot-windows-x64/VERSION

@@ -1 +1 @@
-1.6.6
+v1.6.7

package/bin/omnibot-windows-x64/certifi/cacert.pem

@@ -23,6 +23,47 @@ fQjGGoe9GKhzvSbKYAydzpmfz1wPMOG+FDHqAjAU9JM8SaczepBGR7NjfRObTrdv
 GDeAU/7dIOA1mjbRxwG55tzd8/8dLDoWV9mSOdY=
 -----END CERTIFICATE-----
 
+# Issuer: O=Chunghwa Telecom Co., Ltd. OU=ePKI Root Certification Authority
+# Subject: O=Chunghwa Telecom Co., Ltd. OU=ePKI Root Certification Authority
+# Label: "ePKI Root Certification Authority"
+# Serial: 28956088682735189655030529057352760477
+# MD5 Fingerprint: 1b:2e:00:ca:26:06:90:3d:ad:fe:6f:15:68:d3:6b:b3
+# SHA1 Fingerprint: 67:65:0d:f1:7e:8e:7e:5b:82:40:a4:f4:56:4b:cf:e2:3d:69:c6:f0
+# SHA256 Fingerprint: c0:a6:f4:dc:63:a2:4b:fd:cf:54:ef:2a:6a:08:2a:0a:72:de:35:80:3e:2f:f5:ff:52:7a:e5:d8:72:06:df:d5
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
+
 # Issuer: CN=NetLock Arany (Class Gold) F\u0151tan\xfas\xedtv\xe1ny O=NetLock Kft. OU=Tan\xfas\xedtv\xe1nykiad\xf3k (Certification Services)
 # Subject: CN=NetLock Arany (Class Gold) F\u0151tan\xfas\xedtv\xe1ny O=NetLock Kft. OU=Tan\xfas\xedtv\xe1nykiad\xf3k (Certification Services)
 # Label: "NetLock Arany (Class Gold) F\u0151tan\xfas\xedtv\xe1ny"
@@ -3528,6 +3569,35 @@ xeSDwWrruoBa3lwtcHb4yOWHh8qgnaHlIhInD0Q9HWzq1MKLL295q39QpsQZp6F6
 t5b5wR9iWqJDB0BeJsas7a5wFsWqynKKTbDPAYsDP27X
 -----END CERTIFICATE-----
 
+# Issuer: CN=SecureSign Root CA12 O=Cybertrust Japan Co., Ltd.
+# Subject: CN=SecureSign Root CA12 O=Cybertrust Japan Co., Ltd.
+# Label: "SecureSign Root CA12"
+# Serial: 587887345431707215246142177076162061960426065942
+# MD5 Fingerprint: c6:89:ca:64:42:9b:62:08:49:0b:1e:7f:e9:07:3d:e8
+# SHA1 Fingerprint: 7a:22:1e:3d:de:1b:06:ac:9e:c8:47:70:16:8e:3c:e5:f7:6b:06:f4
+# SHA256 Fingerprint: 3f:03:4b:b5:70:4d:44:b2:d0:85:45:a0:20:57:de:93:eb:f3:90:5f:ce:72:1a:cb:c7:30:c0:6d:da:ee:90:4e
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
+
 # Issuer: CN=SecureSign Root CA14 O=Cybertrust Japan Co., Ltd.
 # Subject: CN=SecureSign Root CA14 O=Cybertrust Japan Co., Ltd.
 # Label: "SecureSign Root CA14"

package/bin/omnibot-windows-x64/omnibot/skills/omnibot/SKILL.md

@@ -1,261 +1,220 @@
----
-name: omnibot
-description: Use when AI agents need to read, inspect, operate, navigate, debug, or verify browser state through the omnibot CLI and connected Chromium extension.
-compatibility: Requires omnibot v2 CLI daemon and the omnibot Chromium extension connected to 127.0.0.1:18765.
-allowed-tools: Bash
-metadata:
-  author: omnibot
-  version: "2.4.0"
----
-
-# Omnibot
-
-Omnibot is Browser Infrastructure for AI Agents.
-
-It connects Hermes, Claude Code, Codex, OpenCode, and other agent systems to a real Chromium browser through the local omnibot daemon and CLI.
-
-This skill is an execution specification for agents. It is not a human command manual.
-
-## When to Use
-
-- Use Omnibot when browser runtime state matters: login, cookies, storage, client-side rendering, extensions, or visible user tabs.
-- Use Omnibot when an agent must read rendered pages, click controls, fill forms, navigate, extract content, or collect evidence.
-- Do not use Omnibot when static files or plain HTTP content already answer the task.
-
-## Core Rules
-
-- Reliability > Convenience.
-- Explicit State > Implicit State.
-- Pattern > Command.
-- Observe -> Act -> Verify.
-- Fallback is allowed, but never first.
-- Do not use `execute-js` first.
-- Run `omnibot <command> --help` before using uncommon or newly introduced commands, especially `batch`, `network`, `cdp`, `record`, `trace`, and `skills`.
-- If a command from memory fails with parser errors, stop using that remembered syntax and re-check `omnibot --help` plus the subcommand help.
-- Prefer semantic locators and `snapshot -i` refs before selectors.
-- Raw `cdp` calls are one-shot. Do not assume `Network.enable` alone creates readable logs. For API/request evidence, use `network clear -> network start -> one action -> network stop -> network logs/summary`.
-- After a failed click by ref, re-observe or use a higher-evidence fallback. Do not keep using stale `@eN` refs from a previous snapshot.
-- For shopping, checkout, payment, banking, or irreversible workflows: Do not click final submit/pay/place-order controls unless the user explicitly confirms that final action in the current turn.
-- Prefer condition-based `wait` over shell sleep.
-- Parse JSON output from commands that return JSON.
-- Do not claim success without verification evidence.
-
-## Workflow Context + Tab Target
-
-Every page-state workflow must use both controls:
-
-- `OMNIBOT_SESSION_TOKEN=<workflow-name>` for workflow isolation.
-- `--tab-id <TAB_ID>` for page targeting.
-
-OMNIBOT_SESSION_TOKEN is a workflow/context token, not a browser session and not a tab target. It isolates agent state such as refs, trace, recording, aliases, and temporary resources. Tab ID controls which page receives the command.
-
-Do not rely on default tab, active tab, current tab, or prior targeting state. Every page-state command requires explicit `--tab-id` except when the command is only discovering or creating a tab.
-
-Use the same token inside one workflow. Use different tokens for independent workflows.
-
-Standard form:
-
-```bash
-OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=research omnibot click --tab-id <TAB_ID> @e4
-OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
-```
-
-`@eN` refs are tab-scoped. Refs rule: never reuse `@eN` refs across tabs.
-
-The agent dispatch pattern is token + tab-id:
-
-1. Set a stable `OMNIBOT_SESSION_TOKEN`.
-2. Discover or create the target tab.
-3. Save the returned tab id.
-4. Pass `--tab-id <TAB_ID>` on every command that touches page state.
-5. Run observe -> act -> verify on that same tab.
-
-Examples of tab-locked page-state commands:
-
-```bash
-OMNIBOT_SESSION_TOKEN=checkout omnibot get value "input[name=email]" --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=checkout omnibot find placeholder "Search" --action type --action-value "omnibot" --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=checkout omnibot dom dblclick n1 --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=checkout omnibot clipboard read --tab-id <TAB_ID>
-```
-
-Targeting categories:
-
-| Command category | Rule |
-| --- | --- |
-| Page-state commands: `snapshot`, `click`, `fill`, `type`, `get`, `is`, `wait`, `screenshot`, `console`, `network`, `execute-js`, `dom`, `mouse`, `clipboard`, `viewport`, `assets`, `goto`, same-tab `navigate` | Require `--tab-id <TAB_ID>`. |
-| Discovery or tab creation: `tabs`, `tab list`, `tab new <URL>`, `open <URL>`, `navigate <URL>` | Return or discover the tab id; save it for later page-state commands. |
-| Read URL exception: `read <URL>` | Opens a temporary read tab and does not need `--tab-id`; reading an existing tab still requires `read --tab-id <TAB_ID>`. |
-
-## Observe -> Act -> Verify
-
-All page operations must follow this loop:
-
-1. Observe the current page state.
-2. Act once using the highest reliable pattern available.
-3. Verify the expected state change.
-
-Click example:
-
-```bash
-OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=research omnibot click --tab-id <TAB_ID> @e4
-OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
-```
-
-Read/verify example:
-
-```bash
-OMNIBOT_SESSION_TOKEN=checkout omnibot is enabled "button[type=submit]" --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=checkout omnibot find role button --name "Submit" --action click --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=checkout omnibot wait --url "/dashboard" --tab-id <TAB_ID>
-OMNIBOT_SESSION_TOKEN=checkout omnibot get url --tab-id <TAB_ID>
-```
-
-If verification fails, do not repeat blindly. Re-observe, choose the next fallback tier, and verify again.
-
-## Pattern > Command
-
-Start from the task, not the command name. Use operation patterns for read, click, fill, select/check, navigation, wait, extraction, and batch.
-
-Use fallback tiers only after standard patterns fail. Collect evidence separately from fallback execution. The command reference is only a lookup table; it must not decide behavior.
-
-## Read vs Snapshot Routing
-
-Choose by intent before choosing by command name:
-
-| Intent | Prefer | Why |
-| --- | --- | --- |
-| Summarize or extract page content, article text, search results, feeds, or long/lazy pages | `read` | Returns clean text/Markdown for agent reasoning. |
-| Quickly observe current visible UI structure before deciding what to do next | `snapshot -i` | Returns actionable refs and page structure for routing. |
-| Find buttons, links, inputs, or refs for a later action | `find` or `snapshot -i` | Produces actionable targets; `read` does not. |
-| Verify one concrete condition | `get`, `is`, or `wait` | Narrow evidence is more reliable than dumping a page. |
-
-Do not use `read` as the first step for click/fill workflows unless the user explicitly asked for page content first.
-
-## Dropdowns And Custom Comboboxes
-
-`snapshot -i` may auto-probe visible custom comboboxes and append their options as refs. If the output lists `@eN [option] "..."`, click that option ref directly; Omnibot will reopen the owning combobox through `openerSelector` if the dropdown closed during snapshot.
-
-Use `select @combobox "value"` for native selects or simple controls. Use `click @option` when `snapshot -i` exposes auto-probed combobox option refs. Do not manually reopen every dropdown just to discover options unless `snapshot -i` did not expose option refs.
-
-## Rich Text Article Editors
-
-ContentEditable rich text editors (ProseMirror, Quill, Draft.js, Slate, ByteDance/Toutiao article body, etc.) are often missing from the AX tree. `snapshot -i` appends them under `# DOM Rich Text Editors` as `@eN [richtext] "..." [contenteditable=true]` refs.
-
-- Detect the body editor: `snapshot -i` → look for `@eN [richtext]` under `# DOM Rich Text Editors`. Do not fill the article body through a `[textbox]` title ref.
-- Replace the whole body: `fill @richtext "paragraph 1\n\nparagraph 2"`. Empty lines split paragraphs; the previous content is cleared and `input`/`change` events are dispatched.
-- Append to the body: `type @richtext " additional text"`.
-- Focus before keyboard input: click `@richtext` first, then `press`/`keyboard`.
-- Raw selector fallback: `omnibot fill '[contenteditable="true"]' "..."` also routes through the rich text path when the selector looks like a rich editor.
-
-Do not use `execute-js` first for rich text writes; `fill`/`type` on the `[richtext]` ref is the supported path.
-
-## Quick Routing
-
-| Need | Read |
-| --- | --- |
-| Runtime check | `references/runtime-and-status.md` |
-| Reading pages | `references/operation-patterns.md#read` |
-| Clicking | `references/operation-patterns.md#click` |
-| Filling forms | `references/operation-patterns.md#fill` |
-| Select / check | `references/operation-patterns.md#select--check` |
-| Navigation | `references/operation-patterns.md#navigation` |
-| Waiting | `references/operation-patterns.md#wait` |
-| Extraction | `references/operation-patterns.md#extraction` |
-| Batch | `references/operation-patterns.md#batch` |
-| Fallback | `references/fallback-operations.md` |
-| Tabs and sessions | `references/session-and-tabs.md` |
-| Debug evidence | `references/debugging-and-evidence.md` |
-| Network/API capture | `references/debugging-and-evidence.md#network-capture` |
-| Commands | `references/command-reference.md` |
-| Anti-patterns | `references/anti-patterns.md` |
-
-## Runtime First
-
-Before troubleshooting browser behavior, check runtime state:
-
-```bash
-omnibot doctor
-omnibot tabs
-omnibot visibility status
-omnibot browser current
-omnibot license status
-```
-
-If the extension is not connected, open Chrome or Edge with the omnibot extension loaded and keep an HTTP/HTTPS tab open.
-
-## Site Memory Reuse
-
-Before operating a complex site, check whether a generated site skill is installed for the current domain.
-
-1. Run `omnibot skills list-sites` to see available generated site skills.
-2. If a matching site skill is installed (e.g., `omnibot-xhs`), read its `SKILL.md` and use it for the operation.
-3. If no matching site skill is installed, create one with:
-   ```bash
-   omnibot explore run <url> --name <site> --goal "<explicit goal>"
-   omnibot skills install --agent opencode --site <site>
-   ```
-4. Generated site skills are not auto-loaded from `~/.omnibot/skills/`; they must be installed into the current agent's skill directory.
-
-## Generated Site Skill Installation
-
-Generated site skills are stored under `~/.omnibot/skills/omnibot-<name>/` but must be installed into each agent's native skill path to be auto-loaded.
-
-List available generated site skills:
-
-```bash
-omnibot skills list-sites
-```
-
-Install one generated site skill:
-
-```bash
-omnibot skills install --agent opencode --site xhs
-omnibot skills install --agent claude --site xhs
-omnibot skills install --agent codex --site xhs
-```
-
-Install all generated site skills:
-
-```bash
-omnibot skills install --agent opencode --all-sites
-```
-
-Default `omnibot skills install --agent <agent>` installs only the official packaged omnibot skill, not generated site skills.
-
-Local site memory is reusable strategy, not user task output. Do not write user inputs, scraped records, or private task results into generated site packages.
-
-## Fallback Discipline
-
-Fallback tiers are for completing operations after better patterns fail. They are not debugging shortcuts.
-
-Tier order:
-
-1. Semantic `find`.
-2. `snapshot -i` refs.
-3. Selectors.
-4. `dom` fallback.
-5. `mouse` fallback.
-6. `execute-js` fallback.
-7. Raw `cdp` fallback.
-
-When entering a lower tier, state why the higher tier failed. After any fallback action, verify with `snapshot`, `get`, `is`, `wait`, or equivalent evidence.
-
-## Debug Evidence
-
-Debugging is for evidence. Fallback is for completing operations.
-
-Use screenshots, annotated screenshots, console logs, network logs, trace, record/replay, and CDP inspection to explain failures or prove state. Do not treat `execute-js` as ordinary debug output.
-
-## Absolute Prohibitions
-
-- Missing `OMNIBOT_SESSION_TOKEN` or missing `--tab-id` on page-state commands.
-- Acting without verify or claiming success without evidence.
-- Using `execute-js` first, raw CSS before semantic find, `@eN` across tabs, implicit tab targeting, or shell sleep instead of `omnibot wait`.
-- Using removed commands: `switch-tab`, `focus-tab`, `tab switch`, `tab focus`. These are no longer available.
-- Using `tabs[0]` or the first tab as a target. The first tab is often a user tab or transport tab.
-- Closing user tabs discovered during cleanup. Only close tabs created by the current workflow.
-
-See `references/anti-patterns.md` before using shortcuts.
+---
+name: omnibot
+description: Use when AI agents need to read, inspect, operate, navigate, debug, or verify browser state through the omnibot CLI and connected Chromium extension.
+compatibility: Requires omnibot v2 CLI daemon and the omnibot Chromium extension connected to 127.0.0.1:18765.
+allowed-tools: Bash
+metadata:
+  author: omnibot
+  version: "2.4.0"
+---
+
+# Omnibot
+
+Omnibot is Browser Infrastructure for AI Agents.
+
+It connects Hermes, Claude Code, Codex, OpenCode, and other agent systems to a real Chromium browser through the local omnibot daemon and CLI.
+
+This skill is an execution specification for agents. It is not a human command manual.
+
+## When to Use
+
+- Use Omnibot when browser runtime state matters: login, cookies, storage, client-side rendering, extensions, or visible user tabs.
+- Use Omnibot when an agent must read rendered pages, click controls, fill forms, navigate, extract content, or collect evidence.
+- Do not use Omnibot when static files or plain HTTP content already answer the task.
+
+## Core Rules
+
+- Reliability > Convenience.
+- Explicit State > Implicit State.
+- Pattern > Command.
+- Observe -> Act -> Verify.
+- Fallback is allowed, but never first.
+- Do not use `execute-js` first.
+- Run `omnibot <command> --help` before using uncommon or newly introduced commands, especially `batch`, `network`, `cdp`, `record`, `trace`, and `skills`.
+- If a command from memory fails with parser errors, stop using that remembered syntax and re-check `omnibot --help` plus the subcommand help.
+- Prefer semantic locators and `snapshot -i` refs before selectors.
+- Raw `cdp` calls are one-shot. Do not assume `Network.enable` alone creates readable logs. For API/request evidence, use `network clear -> network start -> one action -> network stop -> network logs/summary`.
+- After a failed click by ref, re-observe or use a higher-evidence fallback. Do not keep using stale `@eN` refs from a previous snapshot.
+- For shopping, checkout, payment, banking, or irreversible workflows: Do not click final submit/pay/place-order controls unless the user explicitly confirms that final action in the current turn.
+- Prefer condition-based `wait` over shell sleep.
+- Parse JSON output from commands that return JSON.
+- Do not claim success without verification evidence.
+
+## Workflow Context + Tab Target
+
+Every page-state workflow must use both controls:
+
+- `OMNIBOT_SESSION_TOKEN=<workflow-name>` for workflow isolation.
+- `--tab-id <TAB_ID>` for page targeting.
+
+OMNIBOT_SESSION_TOKEN is a workflow/context token, not a browser session and not a tab target. It isolates agent state such as refs, trace, recording, aliases, and temporary resources. Tab ID controls which page receives the command.
+
+Do not rely on default tab, active tab, current tab, or prior targeting state. Every page-state command requires explicit `--tab-id` except when the command is only discovering or creating a tab.
+
+Use the same token inside one workflow. Use different tokens for independent workflows.
+
+Standard form:
+
+```bash
+OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=research omnibot click --tab-id <TAB_ID> @e4
+OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
+```
+
+`@eN` refs are tab-scoped. Refs rule: never reuse `@eN` refs across tabs.
+
+The agent dispatch pattern is token + tab-id:
+
+1. Set a stable `OMNIBOT_SESSION_TOKEN`.
+2. Discover or create the target tab.
+3. Save the returned tab id.
+4. Pass `--tab-id <TAB_ID>` on every command that touches page state.
+5. Run observe -> act -> verify on that same tab.
+
+Examples of tab-locked page-state commands:
+
+```bash
+OMNIBOT_SESSION_TOKEN=checkout omnibot get value "input[name=email]" --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=checkout omnibot find placeholder "Search" --action type --action-value "omnibot" --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=checkout omnibot dom dblclick n1 --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=checkout omnibot clipboard read --tab-id <TAB_ID>
+```
+
+Targeting categories:
+
+| Command category | Rule |
+| --- | --- |
+| Page-state commands: `snapshot`, `click`, `fill`, `type`, `get`, `is`, `wait`, `screenshot`, `console`, `network`, `execute-js`, `dom`, `mouse`, `clipboard`, `viewport`, `assets`, `goto`, same-tab `navigate` | Require `--tab-id <TAB_ID>`. |
+| Discovery or tab creation: `tabs`, `tab list`, `tab new <URL>`, `open <URL>`, `navigate <URL>` | Return or discover the tab id; save it for later page-state commands. |
+| Read URL exception: `read <URL>` | Opens a temporary read tab and does not need `--tab-id`; reading an existing tab still requires `read --tab-id <TAB_ID>`. |
+
+## Observe -> Act -> Verify
+
+All page operations must follow this loop:
+
+1. Observe the current page state.
+2. Act once using the highest reliable pattern available.
+3. Verify the expected state change.
+
+Click example:
+
+```bash
+OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=research omnibot click --tab-id <TAB_ID> @e4
+OMNIBOT_SESSION_TOKEN=research omnibot snapshot -i --tab-id <TAB_ID>
+```
+
+Read/verify example:
+
+```bash
+OMNIBOT_SESSION_TOKEN=checkout omnibot is enabled "button[type=submit]" --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=checkout omnibot find role button --name "Submit" --action click --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=checkout omnibot wait --url "/dashboard" --tab-id <TAB_ID>
+OMNIBOT_SESSION_TOKEN=checkout omnibot get url --tab-id <TAB_ID>
+```
+
+If verification fails, do not repeat blindly. Re-observe, choose the next fallback tier, and verify again.
+
+## Pattern > Command
+
+Start from the task, not the command name. Use operation patterns for read, click, fill, select/check, navigation, wait, extraction, and batch.
+
+Use fallback tiers only after standard patterns fail. Collect evidence separately from fallback execution. The command reference is only a lookup table; it must not decide behavior.
+
+## Read vs Snapshot Routing
+
+Choose by intent before choosing by command name:
+
+| Intent | Prefer | Why |
+| --- | --- | --- |
+| Summarize or extract page content, article text, search results, feeds, or long/lazy pages | `read` | Returns clean text/Markdown for agent reasoning. |
+| Quickly observe current visible UI structure before deciding what to do next | `snapshot -i` | Returns actionable refs and page structure for routing. |
+| Find buttons, links, inputs, or refs for a later action | `find` or `snapshot -i` | Produces actionable targets; `read` does not. |
+| Verify one concrete condition | `get`, `is`, or `wait` | Narrow evidence is more reliable than dumping a page. |
+
+Do not use `read` as the first step for click/fill workflows unless the user explicitly asked for page content first.
+
+## Dropdowns And Custom Comboboxes
+
+`snapshot -i` may auto-probe visible custom comboboxes and append their options as refs. If the output lists `@eN [option] "..."`, click that option ref directly; Omnibot will reopen the owning combobox through `openerSelector` if the dropdown closed during snapshot.
+
+Use `select @combobox "value"` for native selects or simple controls. Use `click @option` when `snapshot -i` exposes auto-probed combobox option refs. Do not manually reopen every dropdown just to discover options unless `snapshot -i` did not expose option refs.
+
+## Rich Text Article Editors
+
+ContentEditable rich text editors (ProseMirror, Quill, Draft.js, Slate, ByteDance/Toutiao article body, etc.) are often missing from the AX tree. `snapshot -i` appends them under `# DOM Rich Text Editors` as `@eN [richtext] "..." [contenteditable=true]` refs.
+
+- Detect the body editor: `snapshot -i` → look for `@eN [richtext]` under `# DOM Rich Text Editors`. Do not fill the article body through a `[textbox]` title ref.
+- Replace the whole body: `fill @richtext "paragraph 1\n\nparagraph 2"`. Empty lines split paragraphs; the previous content is cleared and `input`/`change` events are dispatched.
+- Append to the body: `type @richtext " additional text"`.
+- Focus before keyboard input: click `@richtext` first, then `press`/`keyboard`.
+- Raw selector fallback: `omnibot fill '[contenteditable="true"]' "..."` also routes through the rich text path when the selector looks like a rich editor.
+
+Do not use `execute-js` first for rich text writes; `fill`/`type` on the `[richtext]` ref is the supported path.
+
+## Quick Routing
+
+| Need | Read |
+| --- | --- |
+| Runtime check | `references/runtime-and-status.md` |
+| Reading pages | `references/operation-patterns.md#read` |
+| Clicking | `references/operation-patterns.md#click` |
+| Filling forms | `references/operation-patterns.md#fill` |
+| Select / check | `references/operation-patterns.md#select--check` |
+| Navigation | `references/operation-patterns.md#navigation` |
+| Waiting | `references/operation-patterns.md#wait` |
+| Extraction | `references/operation-patterns.md#extraction` |
+| Batch | `references/operation-patterns.md#batch` |
+| Fallback | `references/fallback-operations.md` |
+| Tabs and sessions | `references/session-and-tabs.md` |
+| Debug evidence | `references/debugging-and-evidence.md` |
+| Network/API capture | `references/debugging-and-evidence.md#network-capture` |
+| Commands | `references/command-reference.md` |
+| Anti-patterns | `references/anti-patterns.md` |
+
+## Runtime First
+
+Before troubleshooting browser behavior, check runtime state:
+
+```bash
+omnibot doctor
+omnibot tabs
+omnibot visibility status
+omnibot browser current
+omnibot license status
+```
+
+If the extension is not connected, open Chrome or Edge with the omnibot extension loaded and keep an HTTP/HTTPS tab open.
+
+## Fallback Discipline
+
+Fallback tiers are for completing operations after better patterns fail. They are not debugging shortcuts.
+
+Tier order:
+
+1. Semantic `find`.
+2. `snapshot -i` refs.
+3. Selectors.
+4. `dom` fallback.
+5. `mouse` fallback.
+6. `execute-js` fallback.
+7. Raw `cdp` fallback.
+
+When entering a lower tier, state why the higher tier failed. After any fallback action, verify with `snapshot`, `get`, `is`, `wait`, or equivalent evidence.
+
+## Debug Evidence
+
+Debugging is for evidence. Fallback is for completing operations.
+
+Use screenshots, annotated screenshots, console logs, network logs, trace, record/replay, and CDP inspection to explain failures or prove state. Do not treat `execute-js` as ordinary debug output.
+
+## Absolute Prohibitions
+
+- Missing `OMNIBOT_SESSION_TOKEN` or missing `--tab-id` on page-state commands.
+- Acting without verify or claiming success without evidence.
+- Using `execute-js` first, raw CSS before semantic find, `@eN` across tabs, implicit tab targeting, or shell sleep instead of `omnibot wait`.
+- Using removed commands: `switch-tab`, `focus-tab`, `tab switch`, `tab focus`. These are no longer available.
+- Using `tabs[0]` or the first tab as a target. The first tab is often a user tab or transport tab.
+- Closing user tabs discovered during cleanup. Only close tabs created by the current workflow.
+
+See `references/anti-patterns.md` before using shortcuts.