@weavetab/skills 2.5.0-beta.4 → 2.5.0

package/dist/bundled/weavetab-browser.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: BROWSER
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## dom-strategy

package/dist/bundled/weavetab-desktop.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: DESKTOP
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## desktop-targeting

package/dist/bundled/weavetab-developer.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: DEVELOPER
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## github-forensics

package/dist/bundled/weavetab-documents.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: DOCUMENTS
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## canvas-and-visual-capture

package/dist/bundled/weavetab-memory.md

@@ -1,196 +1,196 @@
 # Weavetab Domain Profile: MEMORY
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## selector-memory-system
 
-# Two-Tier Memory System
-
-Weavetab operates a two-tier persistent memory system. Understanding both layers prevents wasted DOM traversals and makes agents dramatically faster across sessions.
-
----
-
-## Tier 1 — Selector Confidence Cache (`~/.weavetab-system/memory/`)
-
-Per-domain JSON files (one per hostname) track individual element selectors and their interaction history.
-
-Every time an element is located and interacted with, Weavetab calculates a confidence score based on:
-1. **Attribute Stability**: Prefers `data-testid`, `id`, `aria-label`, and semantic roles over dynamic Tailwind/CSS-module class strings.
-2. **Success Count**: Selectors that successfully trigger navigation or state changes gain reinforcement.
-3. **Origin Isolation**: Learned selectors are strictly namespaced to the origin to prevent cross-site contamination.
-
-### Strike Degradation
-- **Strike 1**: Marked as degraded — falls back to secondary candidates or fuzzy label match.
-- **Strike 2**: Deprecated — immediate fallback to full DOM inspection via `browser_find` or `browser_map`.
-- **Strike 3**: Purged from memory cache to prevent stale lookups.
-
-### Agent Discipline for Tier 1
-1. **Rely on Native Tool Resolution**: When you pass a `ref`, Weavetab queries both the active volatile registry and the Tier 1 memory cache automatically.
-2. **Don't Hardcode Fragile Selectors**: Never pass brittle absolute CSS paths like `div:nth-child(3) > ul > li:nth-child(2) > button`.
-3. **Trust Heuristic Recovery**: If a button moves slightly on the page, the underlying engine re-anchors before reporting failure.
-
----
-
-## Tier 2 — Site Profiles & Workflow Patterns (`~/.weavetab-system/memory/sites/`)
-
-One JSON file per origin stores named multi-step workflow patterns, site quirks, and reliability scores. This is the **Intelligent Memory** layer — agents learn entire flows, not just individual selectors.
-
-### Checking a Site Profile at Session Start
-Always call `browser_pattern_learn` with `action: "get"` when starting an automation session on a site you may have visited before:
-
-```json
-{ "origin": "https://github.com" }
-```
-
-Response tells you:
-- `known_patterns`: named flows with reliability scores and step counts
-- `quirks`: known cookie banners, rate limits, modal popups to handle automatically
-- `framework`: detected frontend stack
-- `_hint`: compact hint string summarizing everything
-
-### Fast-Path Decision Rule
-| Reliability | Action |
-|---|---|
-| **≥ 0.8** | Use pattern steps directly via `browser_burst` — skip exploratory navigation |
-| **0.5 – 0.79** | Attempt pattern but verify success indicator before moving on |
-| **< 0.5 or strikes ≥ 3** | Ignore pattern, re-explore from scratch, then teach via `browser_pattern_learn` |
-
-### Teaching a New Pattern After Completing a Workflow
-After successfully completing a multi-step flow:
-
-```json
-{
-  "origin": "https://github.com",
-  "action": "learn",
-  "name": "login_flow",
-  "steps": [
-    { "tool": "browser_click", "target": ".btn-login" },
-    { "tool": "browser_fill", "target": "#login_field", "value": "{{username}}" },
-    { "tool": "browser_fill", "target": "#password", "value": "{{password}}" },
-    { "tool": "browser_click", "target": "[type=submit]" }
-  ],
-  "success_indicator": "a[aria-label='Homepage']"
-}
-```
-
-### Recording Execution Outcomes (Reliability Upkeep)
-After replaying a pattern, always report the outcome:
-
-```json
-{
-  "origin": "https://github.com",
-  "action": "record_execution",
-  "name": "login_flow",
-  "success": true,
-  "duration_ms": 3200
-}
-```
-
-### Recording Site Quirks
-When you discover a cookie banner or rate limit:
-
-```json
-{
-  "origin": "https://github.com",
-  "action": "record_quirk",
-  "quirk_key": "cookie_banner",
-  "quirk_data": { "selector": "#cookie-consent", "action": "click .accept-all", "appears": "first_visit" }
-}
-```
-
-On future visits, the quirk is present in the profile so you can dismiss banners before starting your main workflow — zero wasted agent turns.
-
----
-
-## File Locations (Never Write to ~/.weavetab/)
-
-| Tier | Path | Owner |
-|---|---|---|
-| Tier 1 selectors | `~/.weavetab-system/memory/<hostname>.json` | Engine (auto) |
-| Tier 2 site profiles | `~/.weavetab-system/memory/sites/<origin>.json` | Engine via `browser_pattern_learn` |
-| Knowledge hints | `~/.weavetab-system/knowledge/<hostname>.md` | Engine (auto, 20-token notes) |
+# Two-Tier Memory System
+
+Weavetab operates a two-tier persistent memory system. Understanding both layers prevents wasted DOM traversals and makes agents dramatically faster across sessions.
+
+---
+
+## Tier 1 — Selector Confidence Cache (`~/.weavetab-system/memory/`)
+
+Per-domain JSON files (one per hostname) track individual element selectors and their interaction history.
+
+Every time an element is located and interacted with, Weavetab calculates a confidence score based on:
+1. **Attribute Stability**: Prefers `data-testid`, `id`, `aria-label`, and semantic roles over dynamic Tailwind/CSS-module class strings.
+2. **Success Count**: Selectors that successfully trigger navigation or state changes gain reinforcement.
+3. **Origin Isolation**: Learned selectors are strictly namespaced to the origin to prevent cross-site contamination.
+
+### Strike Degradation
+- **Strike 1**: Marked as degraded — falls back to secondary candidates or fuzzy label match.
+- **Strike 2**: Deprecated — immediate fallback to full DOM inspection via `browser_find` or `browser_map`.
+- **Strike 3**: Purged from memory cache to prevent stale lookups.
+
+### Agent Discipline for Tier 1
+1. **Rely on Native Tool Resolution**: When you pass a `ref`, Weavetab queries both the active volatile registry and the Tier 1 memory cache automatically.
+2. **Don't Hardcode Fragile Selectors**: Never pass brittle absolute CSS paths like `div:nth-child(3) > ul > li:nth-child(2) > button`.
+3. **Trust Heuristic Recovery**: If a button moves slightly on the page, the underlying engine re-anchors before reporting failure.
+
+---
+
+## Tier 2 — Site Profiles & Workflow Patterns (`~/.weavetab-system/memory/sites/`)
+
+One JSON file per origin stores named multi-step workflow patterns, site quirks, and reliability scores. This is the **Intelligent Memory** layer — agents learn entire flows, not just individual selectors.
+
+### Checking a Site Profile at Session Start
+Always call `browser_pattern_learn` with `action: "get"` when starting an automation session on a site you may have visited before:
+
+```json
+{ "origin": "https://github.com" }
+```
+
+Response tells you:
+- `known_patterns`: named flows with reliability scores and step counts
+- `quirks`: known cookie banners, rate limits, modal popups to handle automatically
+- `framework`: detected frontend stack
+- `_hint`: compact hint string summarizing everything
+
+### Fast-Path Decision Rule
+| Reliability | Action |
+|---|---|
+| **≥ 0.8** | Use pattern steps directly via `browser_burst` — skip exploratory navigation |
+| **0.5 – 0.79** | Attempt pattern but verify success indicator before moving on |
+| **< 0.5 or strikes ≥ 3** | Ignore pattern, re-explore from scratch, then teach via `browser_pattern_learn` |
+
+### Teaching a New Pattern After Completing a Workflow
+After successfully completing a multi-step flow:
+
+```json
+{
+  "origin": "https://github.com",
+  "action": "learn",
+  "name": "login_flow",
+  "steps": [
+    { "tool": "browser_click", "target": ".btn-login" },
+    { "tool": "browser_fill", "target": "#login_field", "value": "{{username}}" },
+    { "tool": "browser_fill", "target": "#password", "value": "{{password}}" },
+    { "tool": "browser_click", "target": "[type=submit]" }
+  ],
+  "success_indicator": "a[aria-label='Homepage']"
+}
+```
+
+### Recording Execution Outcomes (Reliability Upkeep)
+After replaying a pattern, always report the outcome:
+
+```json
+{
+  "origin": "https://github.com",
+  "action": "record_execution",
+  "name": "login_flow",
+  "success": true,
+  "duration_ms": 3200
+}
+```
+
+### Recording Site Quirks
+When you discover a cookie banner or rate limit:
+
+```json
+{
+  "origin": "https://github.com",
+  "action": "record_quirk",
+  "quirk_key": "cookie_banner",
+  "quirk_data": { "selector": "#cookie-consent", "action": "click .accept-all", "appears": "first_visit" }
+}
+```
+
+On future visits, the quirk is present in the profile so you can dismiss banners before starting your main workflow — zero wasted agent turns.
+
+---
+
+## File Locations (Never Write to ~/.weavetab/)
+
+| Tier | Path | Owner |
+|---|---|---|
+| Tier 1 selectors | `~/.weavetab-system/memory/<hostname>.json` | Engine (auto) |
+| Tier 2 site profiles | `~/.weavetab-system/memory/sites/<origin>.json` | Engine via `browser_pattern_learn` |
+| Knowledge hints | `~/.weavetab-system/knowledge/<hostname>.md` | Engine (auto, 20-token notes) |
 | User config | `~/.weavetab/config.json` | Human — never written by agents |
 
 
 ## session-trail
 
-# Session Trails & Deterministic Macro Compilation
-
-When an agent executes an exploratory workflow (e.g. logging into a dashboard, navigating to analytics, setting date filters, and downloading a CSV), re-running that flow autonomously in the future should not require 15 reasoning steps.
-
-`browser_burst` with `compile_from_history: true` automatically converts recent successful session actions into a high-performance, deterministic execution script.
-
----
-
-## 1. Compiling and Replaying Recent Actions (`browser_burst`)
-
-Replay recent successful actions directly in a single turn:
-
-```json
-{
-  "compile_from_history": true
-}
-```
-
-Or pass `dry_run: true` to inspect the compiled macro steps before running them:
-
-```json
-{
-  "compile_from_history": true,
-  "dry_run": true,
-  "history_limit": 15
-}
-```
-
-### Response Example:
-```json
-{
-  "success": true,
-  "steps_completed": 0,
-  "compiled_steps": [
-    { "tool": "browser_go", "args": { "url": "https://analytics.example.com" } },
-    { "tool": "browser_fill", "args": { "ref": "w:12", "value": "metrics" } },
-    { "tool": "click_and_wait", "args": { "ref": "w:15" } }
-  ],
-  "message": "compiled 3 macro steps from history"
-}
-```
-
----
-
-## 2. Parameterizing Variable Inputs
-
-When `"parameterizeInputs": true` is passed:
-- Text inputs and dates entered during the exploratory session are replaced with named parameters.
-- Secrets entered via `browser_type_secret` are never hardcoded; they are replaced with environment variable or secret lookups.
-
----
-
-## 3. Replaying Compiled Automations
-
-Compiled macros can be executed in sub-second time without LLM inference overhead using `browser_automation`:
-
-```json
-{
-  "macroId": "macro_8f7b2c",
-  "parameters": {
-    "startDate": "2026-09-01",
-    "endDate": "2026-09-03"
-  }
-}
-```
-
----
-
-## 4. Emitting Operational Thoughts (`browser_thoughts`)
-
-Log agent rationale and internal reasoning directly to the Weavetab HUD and telemetry stream without bloating user chat responses:
-
-```json
-{
-  "thought": "Detected dynamic React hydration delay. Holding interaction until DOM mutation settles."
-}
+# Session Trails & Deterministic Macro Compilation
+
+When an agent executes an exploratory workflow (e.g. logging into a dashboard, navigating to analytics, setting date filters, and downloading a CSV), re-running that flow autonomously in the future should not require 15 reasoning steps.
+
+`browser_burst` with `compile_from_history: true` automatically converts recent successful session actions into a high-performance, deterministic execution script.
+
+---
+
+## 1. Compiling and Replaying Recent Actions (`browser_burst`)
+
+Replay recent successful actions directly in a single turn:
+
+```json
+{
+  "compile_from_history": true
+}
+```
+
+Or pass `dry_run: true` to inspect the compiled macro steps before running them:
+
+```json
+{
+  "compile_from_history": true,
+  "dry_run": true,
+  "history_limit": 15
+}
+```
+
+### Response Example:
+```json
+{
+  "success": true,
+  "steps_completed": 0,
+  "compiled_steps": [
+    { "tool": "browser_navigate", "args": { "url": "https://analytics.example.com" } },
+    { "tool": "browser_fill", "args": { "ref": "w:12", "value": "metrics" } },
+    { "tool": "click_and_wait", "args": { "ref": "w:15" } }
+  ],
+  "message": "compiled 3 macro steps from history"
+}
+```
+
+---
+
+## 2. Parameterizing Variable Inputs
+
+When `"parameterizeInputs": true` is passed:
+- Text inputs and dates entered during the exploratory session are replaced with named parameters.
+- Secrets entered via `browser_type_secret` are never hardcoded; they are replaced with environment variable or secret lookups.
+
+---
+
+## 3. Replaying Compiled Automations
+
+Compiled macros can be executed in sub-second time without LLM inference overhead using `browser_automation`:
+
+```json
+{
+  "macroId": "macro_8f7b2c",
+  "parameters": {
+    "startDate": "2026-09-01",
+    "endDate": "2026-09-03"
+  }
+}
+```
+
+---
+
+## 4. Emitting Operational Thoughts (`browser_thoughts`)
+
+Log agent rationale and internal reasoning directly to the Weavetab HUD and telemetry stream without bloating user chat responses:
+
+```json
+{
+  "thought": "Detected dynamic React hydration delay. Holding interaction until DOM mutation settles."
+}
 ```
 
 

package/dist/bundled/weavetab-network-and-perf.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: NETWORK-AND-PERF
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## device-and-environment
@@ -129,7 +129,7 @@ Extract cryptographic handshake metadata, cipher suites, expiration dates, and m
 ```json
 {
   "action": "auditTls",
-  "url": "https://weavetab.pages.dev"
+  "url": "https://weavetab.dev"
 }
 ```
 

package/dist/bundled/weavetab-plugins.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: PLUGINS
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## hooks-and-overrides
@@ -31,48 +31,53 @@ When plugins are active, tool return payloads may include an optional `_pluginMe
 
 ## plugin-runtime
 
-# Plugin Runtime: Dynamic Extension Loading
+# Plugin Runtime: Weavetab Plugin Architecture
 
-Weavetab features an extensible plugin architecture powered by `@weavetab/sdk`. Agents can query loaded extensions and dynamically load community or official plugins into the live MCP runtime without restarting the server.
+Weavetab features an extensible plugin architecture powered by `@weavetab/sdk`. All installed plugins are loaded automatically at server startup — their tools appear directly in the MCP tool list alongside built-in tools. Agents never need to discover or activate plugins manually.
 
 ---
 
-## 1. Inspecting Active Plugins (`list_plugins`)
+## 1. How Plugin Tools Appear
 
-Discover all installed plugins, their versions, and the tools or hooks they expose:
+Plugin tools are first-class MCP tools. If `@weavetab/plugin-recaptcha-solver` is installed, `captcha_solve_token` appears in the tool list immediately on startup — no discovery step needed.
 
-```json
-{}
-```
+There are **no** `list_plugins` or `load_plugin` tools. Managing plugins is a CLI operation:
+
+```bash
+# Install a plugin (restart required)
+weavetab plugin add @weavetab/plugin-youtube
+
+# Remove a plugin
+weavetab plugin rm @weavetab/plugin-youtube
 
-### Response Example:
-```json
-{
-  "plugins": [
-    {
-      "name": "@weavetab/plugin-recaptcha-solver",
-      "version": "1.2.0",
-      "status": "active",
-      "toolsProvided": ["captcha_solve_token"],
-      "hooks": ["beforeToolCall"]
-    }
-  ]
-}
+# List installed plugins
+weavetab plugin list
 ```
 
 ---
 
-## 2. Dynamic Runtime Loading (`load_plugin`)
+## 2. Plugin Permission Model
 
-Load a verified plugin package into the active runtime session:
+Every plugin declares what it can do in `weavetab.json`. The runtime enforces this at load time:
 
-```json
-{
-  "name": "@weavetab/plugin-datadog-tracer"
-}
-```
+| Permission | What it gates |
+|---|---|
+| `tools.add: true` | Plugin can register new MCP tools |
+| `tools.override: ["browser_navigate"]` | Plugin can wrap/replace that built-in tool |
+| `tools.remove: ["browser_pdf"]` | Plugin can disable that built-in tool |
+| `hooks.onBeforeAction: true` | Plugin can intercept all tool calls before execution |
+| `hooks.onAfterAction: true` | Plugin can inspect/transform all tool results |
+
+Plugins that attempt to exceed their declared permissions are blocked with a stderr warning — they do not crash.
+
+---
+
+## 3. Trust Tiers
+
+| Tier | Badge | Condition |
+|---|---|---|
+| Official | `✚ [Official]` | `@weavetab/plugin-*` packages |
+| Verified | `✔ [Verified]` | Listed in the Weavetab verified registry |
+| Unverified | `⚠ [Unverified]` | Unknown community package |
 
-### Plugin Verification Guarantees:
-- Plugins must implement the `@weavetab/sdk` standard interface.
-- Loaded tools become immediately callable by the agent in subsequent turns.
-- If an agent is in the `viewer` RBAC tier, `load_plugin` is rejected with `PERMISSION_DENIED`.
+Unverified plugins are loaded but their permissions are logged visibly at startup for user review.

package/dist/bundled/weavetab-resilience.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: RESILIENCE
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## loop-breaker

package/dist/bundled/weavetab-security.md

@@ -1,6 +1,6 @@
 # Weavetab Domain Profile: SECURITY
 
-Generated for @weavetab/skills v2.5.0-beta.4
+Generated for @weavetab/skills v2.5.0-beta.5
 
 
 ## rbac-and-policies

package/dist/granular/browser_dom-strategy.md

@@ -14,7 +14,7 @@ tools:
   - "browser_scrape"
   - "browser_snapshot"
   - "browser_eval"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # DOM Strategy & Token Conservation Engine

package/dist/granular/browser_form-automation.md

@@ -11,7 +11,7 @@ triggers:
 tools:
   - "browser_fill"
   - "browser_select"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Form Automation: Atomic Multi-Field Execution

package/dist/granular/browser_interaction-pipeline.md

@@ -19,7 +19,7 @@ tools:
   - "browser_burst"
   - "browser_highlight"
   - "browser_clipboard"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Interaction Pipeline: Physical & Synthetic Input Engine

package/dist/granular/browser_tab-and-window.md

@@ -11,7 +11,7 @@ triggers:
   - "desktop app tabs"
 tools:
   - "browser_tabs"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Tab & Window Lifecycle Management

package/dist/granular/desktop_desktop-targeting.md

@@ -15,7 +15,7 @@ tools:
   - "browser_detect"
   - "browser_tabs"
   - "browser_navigate"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Desktop App Targeting & Multi-Window Routing

package/dist/granular/desktop_electron-discovery.md

@@ -10,7 +10,7 @@ triggers:
   - "electron automation"
 tools:
   - "browser_detect"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Electron Discovery & Environment Handshake

package/dist/granular/developer_github-forensics.md

@@ -9,7 +9,7 @@ triggers:
   - "inspect repo"
 tools:
   - "browser_github"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # GitHub Forensics & Repository Architecture Inspection

package/dist/granular/documents_canvas-and-visual-capture.md

@@ -15,7 +15,7 @@ tools:
   - "browser_extract_design"
   - "browser_map"
   - "browser_click"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Visual Capture, Canvas Forensics & Design Extraction

package/dist/granular/documents_office-document-ingestion.md

@@ -10,7 +10,7 @@ triggers:
   - "parse table"
 tools:
   - "browser_office"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Office Document Ingestion: Word, Excel & CSV Parsing

package/dist/granular/memory_selector-memory-system.md

@@ -15,7 +15,7 @@ tools:
   - "browser_click"
   - "browser_fill"
   - "browser_pattern_learn"
-weavetab: ">=2.5.0-beta.4"
+weavetab: ">=2.5.0-beta.5"
 ---
 
 # Two-Tier Memory System