Delete 6 disabled daily agents + clean up stale baselines

Remove documentation, files, media, opportunities, research, and tools
agents — all disabled, never run, no code dependencies. Update test
baselines to also remove stale segment agents (activities, activity,
activity_state, facets, speakers) left over from Segment Sense shipping.

All 109 affected tests pass.

Co-Authored-By: Claude Opus 4.6 (1M context) <[e-mail]>

muse/documentation.md

···
-{
-  "type": "generate",
-
-  "title": "Documentation Moments",
-  "description": "Finds when important knowledge is shared in the transcript and suggests what should be written down. Output is a Markdown list of documentation opportunities with time ranges and destinations.",
-  "occurrences": "Record an occurrence whenever a new procedure, decision or troubleshooting step is described. Capture the related file or tool and where the documentation should live such as wiki or README.",
-  "hook": {"post": "occurrence"},
-  "color": "#007bff",
-  "schedule": "daily",
-  "priority": 10,
-  "disabled": true,
-  "output": "md",
-  "instructions": {
-    "sources": {"transcripts": true, "percepts": false, "agents": {"screen": true}},
-    "facets": true
-  }
-
-}
-
-$daily_preamble
-
-# Workday Documentation Opportunity Analysis
-
-## Objective
-
-Help $preferred capture important knowledge from each workday by analyzing the combined audio and screen transcripts to pinpoint moments when valuable information is shared that should be recorded for future reference.
-
-## Evaluation Goals
-
-1. **Identify Documentable Moments**
-   - Look for explanations of workflows, configuration steps, or troubleshooting techniques.
-   - Note when key decisions or design rationales are discussed.
-   - Capture tips, commands, or best practices mentioned verbally or shown on screen.
-
-2. **Detect Missing Documentation**
-   - Flag situations where someone says they'll document something later, but no record exists.
-   - Notice instructions or clarifications that appear important yet aren't written down elsewhere.
-   - Example: A teammate walking through setup steps during a call that aren't in any README.
-
-3. **Opportunities for Reuse**
-   - Identify explanations or procedures that would benefit others if added to docs.
-   - Highlight repeated questions or confusion that better documentation could resolve.
-
-## Summarizing Documentation Tasks
-
-Create a friendly markdown document output, for each opportunity add a section with a short title and containing:
-
-- **Time Range**: When the discussion or explanation occurred.
-- **Context**: What problem or task was being covered.
-- **Key Details to Capture**: The information that should be documented.
-- **Suggested Destination**: Where to add it (README, wiki, code comment, etc.).
-
-Be concise but thorough—capture anything that would save time later if clearly documented.

muse/files.md

···
-{
-  "type": "generate",
-
-  "title": "File Interactions",
-  "description": "Reviews the day's transcript to capture each significant file or attachment that was opened, saved or shared. Generates a Markdown timeline with context about how the file was used.",
-  "occurrences": "Create an occurrence for every notable file referenced, including the path when known and the related project. Ignore terminal output and focus on visible file explorers or sharing actions.",
-  "hook": {"post": "occurrence"},
-  "color": "#28a745",
-  "schedule": "daily",
-  "priority": 10,
-  "disabled": true,
-  "output": "md",
-  "instructions": {
-    "sources": {"transcripts": true, "percepts": false, "agents": {"screen": true}},
-    "facets": true
-  }
-
-}
-
-$daily_preamble
-
-# Workday File Activity Extraction
-
-## Objective
-
-Analyze a single day's transcript for $name to find every significant specifically named file that was viewed, created, modified, exchanged, or otherwise interacted with during the day. The transcript combines audio conversations and screen summaries in 5‑minute blocks.
-
-## Objectives
-
-1. **Recognize File Interactions**
-   - Detect filenames, directory paths, or file types mentioned aloud or shown on screen.
-   - Include attachments received or sent via email or chat, downloaded items, cloud storage files, and any filesystem locations with visibly selected files.
-   - Note actions such as opening, editing, saving, moving, uploading, or referencing a file.
-
-2. **Capture Context and Location**
-   - Record the surrounding project or task to which the file relates.
-   - Identify where the item resides: local computer, shared drive, Dropbox, Google Drive, email attachment, chat message, downloads folder, etc.
-   - Determine if the usage appears work related or personal.
-
-3. **Ignore Terminal/Console and IDE**
-   - All terminal, console, and IDE output is too noisy
-   - Focus only on workplace tools, file browsing tools, cloud storage, etc.
-   - Most important are files that have been shared or downloaded and opened/viewed.
-
-## Output Format
-
-Produce a friendly markdown document with chronological individual sections with a short title and each containing these items:
-
-- Time Block(s) – starting timestamp of the 5‑minute segment(s).
-- File – name or brief description.
-- Actions – opened, edited, sent, received, downloaded, etc.
-- Location – filesystem path or service (Dropbox, email, chat, etc.).
-- Context – associated project or task.
-- Work/Personal – classify the nature of the content.
-
-Focus on the top few dozen most notable files total. Conclude with a short bullet list summarizing the most important files that shaped the day's work.

muse/media.md

···
-{
-  "type": "generate",
-
-  "title": "Media Consumption",
-  "description": "Identifies when videos, articles, music or social content are consumed. Classifies each instance as work or personal and reports the source in chronological sections.",
-  "occurrences": "Create an occurrence whenever media consumption is noted, noting the application or site and whether it was for work or leisure. Include a short summary of the topic if visible.",
-  "hook": {"post": "occurrence"},
-  "color": "#fd7e14",
-  "schedule": "daily",
-  "priority": 10,
-  "disabled": true,
-  "output": "md",
-  "instructions": {
-    "sources": {"transcripts": true, "percepts": false, "agents": {"screen": true}},
-    "facets": true
-  }
-
-}
-
-$daily_preamble
-
-# Workday Media Consumption Analysis
-
-## Objective
-
-Analyze a single day's transcripts to identify instances of media consumption. The transcripts combine audio and screen summaries in chronological 5‑minute chunks.
-
-## Analysis Tasks
-
-1. **Detect Media Moments**
-   * Review the entire day's transcripts looking for clear signs of media consumption. This includes:
-     - Videos or streaming content
-     - News articles or blog posts
-     - Music or podcasts
-     - Social media browsing
-     - Viewing photos or image galleries
-     - Any other recreational, professional growth, or informational content
-   * Flag both audio mentions and screen evidence (e.g. a YouTube tab, news site, music player, photo viewer, etc.).
-
-2. **Classify Work vs. Personal**
-   * For each media instance, determine whether it appears to be work‑related or personal.
-   * Consider the surrounding context, titles, or content. For example, a technical artical related to a work project is "work," while entertainment videos or casual news are "personal." If uncertain, make your best guess.
-
-3. **Record Topics and Sources**
-   * Capture the main topic or subject matter of the media (technology news, project documentation, politics, entertainment, etc.).
-   * Note the websites or applications involved (e.g. YouTube, Twitter, New York Times, Spotify). Include URLs if visible in the transcript.
-
-## Output Format
-
-Produce a friendly markdown document with chronological individual sections with a short title and each containing these items:
-
-  - Time Segment(s)
-  - Media Type (video, article, music, etc.)
-  - Work or Personal
-  - Topic/Description
-  - Source or Site
-
-At the end add a Summary Insights section with bullet points highlighting overall trends, how much time was spent consuming media, and whether it leaned more toward work or personal purposes.
-
-Be thoughtful, the goal is to surface where time was spent on external content and its relative importance to work and personal life. There should be no more than a few dozen notable items every day.

muse/opportunities.md

···
-{
-  "type": "generate",
-
-  "title": "Innovation Opportunities",
-  "description": "Scans conversations and tasks for sparks of new ideas, problem statements and potential ventures. Outputs a list of the most promising opportunities with context and suggested next steps.",
-  "occurrences": "Whenever a novel idea or pain point is raised, record an occurrence describing the opportunity and any proposed solution. Include who mentioned it and classify the potential impact.",
-  "hook": {"post": "occurrence"},
-  "color": "#20c997",
-  "schedule": "daily",
-  "priority": 10,
-  "disabled": true,
-  "output": "md",
-  "instructions": {
-    "sources": {"transcripts": true, "percepts": false, "agents": {"screen": true}},
-    "facets": true
-  }
-
-}
-
-$daily_preamble
-
-# Workday Innovation Opportunity Discovery
-
-## Objective
-
-Analyze the full workday transcript to identify embryonic ideas, innovation sparks, and potential business opportunities that emerge throughout the day. The transcript combines audio conversations and screen activity organized by recording segments.
-
-## Discovery Framework
-
-### 1. Problem-Solution Signals
-- **Unmet Needs**: Complaints, frustrations, or workarounds that suggest market opportunities
-- **"Wouldn't it be nice if..."**: Wishful thinking statements that reveal innovation potential
-- **Manual Processes**: Repetitive tasks or workflows that could be automated or productized
-- **Tool Gaps**: Missing features or capabilities in existing tools that prompt creative solutions
-
-### 2. Creative Sparks & Ideation
-- **Spontaneous Ideas**: Off-hand comments about potential solutions or new approaches
-- **Cross-Facet Connections**: Moments when concepts from different fields intersect unexpectedly
-- **"What if" Explorations**: Hypothetical scenarios or thought experiments mentioned
-- **Adjacent Possibilities**: Ideas that build on existing work but point to new directions
-
-### 3. Market & Business Signals
-- **Customer Pain Points**: Direct or indirect mentions of owner/customer struggles
-- **Industry Trends**: Discussions about emerging technologies or market shifts
-- **Competitive Gaps**: References to things competitors aren't doing well
-- **Partnership Opportunities**: Potential collaborations or integrations mentioned
-
-### 4. Technical Innovation Seeds
-- **Novel Implementations**: Unique approaches to solving technical problems
-- **Architecture Ideas**: New ways of structuring systems or data flows
-- **Feature Concepts**: Functionality that doesn't exist but was imagined or desired
-- **Integration Opportunities**: Connecting previously unconnected systems or data
-
-### 5. Strategic Opportunities
-- **Pivot Potential**: Discussions that suggest alternative business directions
-- **Market Expansion**: Ideas for reaching new owner segments or use cases
-- **Platform Possibilities**: Concepts that could become foundational for other innovations
-- **Ecosystem Plays**: Opportunities to create or tap into larger systems
-
-## Analysis Approach
-
-1. **Sequential Discovery**
-   - Read chronologically, staying alert for innovation signals
-   - Note both explicit ideas and implicit opportunities
-   - Consider context - some of the best ideas emerge from frustration or constraints
-
-2. **Pattern Recognition**
-   - Look for recurring themes across different conversations or tasks
-   - Identify problems mentioned multiple times or by different people
-   - Notice when similar solutions are independently suggested
-
-3. **Opportunity Assessment**
-   - Gauge the potential impact and feasibility of each opportunity
-   - Consider whether it's a quick experiment or longer-term venture
-   - Note any existing momentum or interest from others
-
-## Output Format
-
-Create a friendly markdown document with individual sections for each opportunity, using a catchy short title, containing:
-
-- **Time Range**: When the opportunity was identified
-- **Context**: The discussion or activity that sparked the idea
-- **Opportunity Description**: What the innovation or business idea entails
-- **Why It Matters**: The problem it solves or value it creates
-- **Next Steps**: Immediate experiments or explorations to validate the concept
-- **Innovation Type**: Quick win / Feature enhancement / New product / Platform / Business model
-
-Focus on the top 10-15 most promising opportunities. Conclude with:
-
-### Innovation Summary
-- **Most Exciting Opportunity**: The single idea with highest potential
-- **Quick Experiments**: 3-5 ideas that could be tested within a week
-- **Strategic Ventures**: 2-3 concepts worth deeper exploration
-- **Cross-Cutting Themes**: Patterns that suggest broader innovation directions
-
-## Special Considerations
-
-- Pay attention to moments of excitement or energy in conversations
-- Note when multiple people express interest in the same concept
-- Look for intersections between personal interests and professional capabilities
-- Consider both B2B and B2C opportunities
-- Include both technical innovations and business model innovations
-- Don't dismiss "small" ideas - they often grow into bigger opportunities
-- Watch for moments when existing solutions are criticized or found lacking
-
-Remember: The goal is to surface nascent opportunities that might otherwise be forgotten, helping transform daily insights into potential ventures or innovations.

muse/research.md

···
-{
-  "type": "generate",
-
-  "title": "Research Needs",
-  "description": "Highlights moments where additional information would help progress work. Produces a list of targeted research tasks with time ranges and context.",
-  "occurrences": "Log an occurrence each time a knowledge gap or open question appears. Mention the problem area and any suggested resources to investigate so the task can be assigned.",
-  "hook": {"post": "occurrence"},
-  "color": "#ff5722",
-  "schedule": "daily",
-  "priority": 10,
-  "disabled": true,
-  "output": "md",
-  "instructions": {
-    "sources": {"transcripts": true, "percepts": false, "agents": {"screen": true}},
-    "facets": true
-  }
-
-}
-
-$daily_preamble
-
-# Workday Research Opportunity Analysis
-
-## Objective
-
-Identify knowledge gaps and compile targeted research tasks by analyzing the day's transcript and screen summaries to spot when additional information would accelerate ongoing projects.
-
-## Evaluation Goals
-
-1. **Assess Deep Work**
-   - Recognize segments of intense focus on a single problem or project.
-   - Note the specific tools, code files, documents or websites visible during these segments.
-   - Example: A 30‑minute block editing `models.py` with no meeting audio indicates deep coding work.
-
-2. **Detect Knowledge Gaps**
-   - Listen for statements such as "I'm not sure," "need to look up," or "I wonder how" in the audio, and no resolution was reached at a later point.
-   - Notice when unfamiliar libraries, APIs, or concepts appear on screen searches or documentation pages.
-   - Example: Searching for "OAuth2 device flow" after a conversation about authentication suggests a research need.
-
-3. **Opportunities for Additional Resources**
-   - Identify when progress stalls, unresolved issues, or tasks are deferred due to missing information.
-   - Notice when there's something that could make a difference and positively impact the workflow but no solution was sought.
-   - Perhaps colleagues can be heard or seen also struggling with an issue, these can be great opportunities to come back and contribute.
-
-## Summarizing Research Topics
-
-Output a friendly markdown document and for each gap or opportunity you find, create a new section with a short title and containing these elements:
-
-- **Time Range**: When the question or issue arose.
-- **Context**: Briefly describe what was being worked on and why the information is needed.
-- **Suggested Research**: A specific topic or set of resources that could be gathered overnight.
-
-## Overnight Research Focus
-
-Prioritize tasks that would provide high value by the start of the next day:
-
-- Documentation reviews or API comparisons.
-- Summaries of best practices related to the current project stack.
-- Example implementations or open‑source references.
-- Any background reading that unblocks upcoming work.
-- Additional things that may help a colleague make progress.
-
-Be concise yet thorough—capture the most important potential items for hitting the ground running tomorrow.

muse/tools.md

···
-{
-  "type": "generate",
-
-  "title": "Tool Usage",
-  "description": "Catalogues every application or service used throughout the day and how long it was active. The report details which tools are critical, supporting or distracting.",
-  "occurrences": "Whenever a tool is launched or actively used, create an occurrence noting the time span, purpose and intensity of use. Distinguish between core work tools and occasional utilities.",
-  "hook": {"post": "occurrence"},
-  "color": "#795548",
-  "schedule": "daily",
-  "priority": 10,
-  "disabled": true,
-  "output": "md",
-  "instructions": {
-    "sources": {"transcripts": true, "percepts": false, "agents": {"screen": true}},
-    "facets": true
-  }
-
-}
-
-$daily_preamble
-
-# Workday Tool Usage Catalog & Analysis
-
-## Objective
-
-Create a comprehensive catalog of technology and tool usage from $pronouns_possessive workday transcript, documenting WHEN, HOW, and WHY each tool was used throughout the day. The transcript combines audio conversations and screen activity organized by recording segments.
-
-## Analysis Framework
-
-### 1. Chronological Tool Usage Catalog
-- **Timeline Mapping**: Document tool usage by recording segments
-- **Usage Duration**: Exact time spent in each application per session
-- **Usage Context**: What task or activity prompted each tool launch
-- **Usage Intensity**: Active use vs. passive background presence
-
-### 2. Tool Importance Classification
-- **Critical Tools**: Applications essential for completing core work tasks
-- **Supporting Tools**: Applications that facilitate or enhance primary workflows
-- **Occasional Tools**: Applications used sporadically for specific needs
-- **Background Tools**: Applications running but minimally interacted with
-- **Distraction Tools**: Applications that interrupt or derail focus
-
-### 3. Usage Pattern Analysis
-- **Peak Usage Windows**: When each tool is most heavily utilized
-- **Tool Combinations**: What applications are commonly used together
-- **Session Patterns**: How long typical tool sessions last
-- **Return Frequency**: How often returning to the same tool throughout the day
-
-### 4. Interaction Depth Analysis
-- **Surface Interactions**: Quick checks, notifications, brief visits
-- **Deep Work Sessions**: Extended focused usage segments
-- **Feature Utilization**: Which specific features/functions are actually used
-- **Keyboard vs. Mouse**: Interaction patterns that indicate proficiency
-
-### 5. Tool Switching Behavior
-- **Trigger Events**: What causes switches between tools (notifications, task completion, interruptions)
-- **Switch Patterns**: Common sequences of tool transitions
-
-### 6. Workflow-Tool Mapping
-- **Task-Tool Relationships**: Which tools are used for specific types of work
-- **Parallel Tool Usage**: Applications used simultaneously for single tasks
-- **Tool Handoffs**: How work moves from one application to another
-
-## Output Format
-
-Create a detailed markdown document with these sections:
-
-### Daily Tool Usage Chronicle
-- **Hour-by-Hour Breakdown**: What tools dominated each hour of the day
-- **Tool Session Log**: Start/stop times for major tool usage segments
-- **Context Annotations**: Brief note on why each tool was used when it was used
-
-### Tool Catalog & Classification
-- **Complete Tool Inventory**: Every application/service touched during the day
-- **Usage Statistics**: Estimated time spent in each tool
-- **Importance Ranking**: Tools ranked by criticality to actual work completion
-
-### Critical Usage Findings
-- **Essential Tool Dependencies**: Tools that block work when unavailable
-- **High-Frequency Micro-Usage**: Tools used in very short but frequent bursts
-- **Deep Work Enablers**: Tools that correlate with extended focus segments
-- **Productivity Multipliers**: Tools that demonstrably accelerate task completion
-- **Time Sinks**: Tools that consume disproportionate time relative to output
-
-Remember: The primary goal is creating an accurate catalog of what tools were actually used, when they were used, and how they contributed to (or detracted from) productive work throughout the day.

tests/baselines/api/agents/agents-day.json

···
 {
   "agents": {
-    "activities": {
-      "app": null,
-      "color": "#00695c",
-      "description": "Detects completed activities across all facets and writes records with synthesized descriptions",
-      "multi_facet": false,
-      "output_format": "json",
-      "schedule": "segment",
-      "source": "system",
-      "title": "Activity Records",
-      "type": "generate"
-    },
-    "activity": {
-      "app": null,
-      "color": "#00bcd4",
-      "description": "Synthesizes segment activity from content, focusing on observable changes and searchability.",
-      "multi_facet": false,
-      "output_format": "md",
-      "schedule": "segment",
-      "source": "system",
-      "title": "Activity Synthesis",
-      "type": "generate"
-    },
-    "activity_state": {
-      "app": null,
-      "color": "#00897b",
-      "description": "Detects configured activities present in segment and tracks state across segments",
-      "multi_facet": true,
-      "output_format": "json",
-      "schedule": "segment",
-      "source": "system",
-      "title": "Activity State",
-      "type": "generate"
-    },
     "anticipation": {
       "app": null,
       "color": "#4527a0",
···
       "schedule": "activity",
       "source": "system",
       "title": "Decision Actions",
-      "type": "generate"
-    },
-    "documentation": {
-      "app": null,
-      "color": "#007bff",
-      "description": "Finds when important knowledge is shared in the transcript and suggests what should be written down. Output is a Markdown list of documentation opportunities with time ranges and destinations.",
-      "multi_facet": false,
-      "output_format": "md",
-      "schedule": "daily",
-      "source": "system",
-      "title": "Documentation Moments",
       "type": "generate"
     },
     "entities": {
···
       "title": "Facet Newsletter Generator",
       "type": "cogitate"
     },
-    "facets": {
-      "app": null,
-      "color": "#7c4dff",
-      "description": "Classifies segment activity into relevant facets based on other segment outputs",
-      "multi_facet": false,
-      "output_format": "json",
-      "schedule": "segment",
-      "source": "system",
-      "title": "Facet Classification",
-      "type": "generate"
-    },
-    "files": {
-      "app": null,
-      "color": "#28a745",
-      "description": "Reviews the day's transcript to capture each significant file or attachment that was opened, saved or shared. Generates a Markdown timeline with context about how the file was used.",
-      "multi_facet": false,
-      "output_format": "md",
-      "schedule": "daily",
-      "source": "system",
-      "title": "File Interactions",
-      "type": "generate"
-    },
     "firstday_checkin": {
       "app": null,
       "color": "#6c757d",
···
       "title": "Knowledge Graph",
       "type": "generate"
     },
-    "media": {
-      "app": null,
-      "color": "#fd7e14",
-      "description": "Identifies when videos, articles, music or social content are consumed. Classifies each instance as work or personal and reports the source in chronological sections.",
-      "multi_facet": false,
-      "output_format": "md",
-      "schedule": "daily",
-      "source": "system",
-      "title": "Media Consumption",
-      "type": "generate"
-    },
     "meetings": {
       "app": null,
       "color": "#e83e8c",
···
       "title": "Onboarding",
       "type": "cogitate"
     },
-    "opportunities": {
-      "app": null,
-      "color": "#20c997",
-      "description": "Scans conversations and tasks for sparks of new ideas, problem statements and potential ventures. Outputs a list of the most promising opportunities with context and suggested next steps.",
-      "multi_facet": false,
-      "output_format": "md",
-      "schedule": "daily",
-      "source": "system",
-      "title": "Innovation Opportunities",
-      "type": "generate"
-    },
     "pulse": {
       "app": null,
       "color": "#6c757d",
···
       "title": "Pulse",
       "type": "cogitate"
     },
-    "research": {
-      "app": null,
-      "color": "#ff5722",
-      "description": "Highlights moments where additional information would help progress work. Produces a list of targeted research tasks with time ranges and context.",
-      "multi_facet": false,
-      "output_format": "md",
-      "schedule": "daily",
-      "source": "system",
-      "title": "Research Needs",
-      "type": "generate"
-    },
     "routine": {
       "app": null,
       "color": "#6c757d",
···
       "title": "Speaker Attribution",
       "type": "generate"
     },
-    "speakers": {
-      "app": null,
-      "color": "#e64a19",
-      "description": "Detects meetings in the segment and extracts participant names from screen and conversation.",
-      "multi_facet": false,
-      "output_format": "json",
-      "schedule": "segment",
-      "source": "system",
-      "title": "Meeting Speakers",
-      "type": "generate"
-    },
     "support:support": {
       "app": "support",
       "color": "#0288d1",
···
       "source": "app",
       "title": "TODO Weekly Scout",
       "type": "cogitate"
-    },
-    "tools": {
-      "app": null,
-      "color": "#795548",
-      "description": "Catalogues every application or service used throughout the day and how long it was active. The report details which tools are critical, supporting or distracting.",
-      "multi_facet": false,
-      "output_format": "md",
-      "schedule": "daily",
-      "source": "system",
-      "title": "Tool Usage",
-      "type": "generate"
     },
     "triage": {
       "app": null,

tests/baselines/api/settings/generators.json

···
     },
     {
       "app": null,
-      "description": "Catalogues every application or service used throughout the day and how long it was active. The report details which tools are critical, supporting or distracting.",
-      "disabled": true,
-      "extract": true,
-      "has_extraction": true,
-      "key": "tools",
-      "source": "system",
-      "title": "Tool Usage"
-    },
-    {
-      "app": null,
       "description": "Constructs a detailed chronological timeline documenting every activity, task shift, and event throughout the workday. Creates a comprehensive historical record with rich descriptions of what happened when.",
       "disabled": false,
       "extract": true,
···
     },
     {
       "app": null,
-      "description": "Finds when important knowledge is shared in the transcript and suggests what should be written down. Output is a Markdown list of documentation opportunities with time ranges and destinations.",
-      "disabled": true,
-      "extract": true,
-      "has_extraction": true,
-      "key": "documentation",
-      "source": "system",
-      "title": "Documentation Moments"
-    },
-    {
-      "app": null,
-      "description": "Highlights moments where additional information would help progress work. Produces a list of targeted research tasks with time ranges and context.",
-      "disabled": true,
-      "extract": true,
-      "has_extraction": true,
-      "key": "research",
-      "source": "system",
-      "title": "Research Needs"
-    },
-    {
-      "app": null,
       "description": "Identifies all future calendar events and scheduled activities noted in transcripts. Extracts dates, times, participants, and event details for anything scheduled beyond today.",
       "disabled": false,
       "extract": true,
···
     },
     {
       "app": null,
-      "description": "Identifies when videos, articles, music or social content are consumed. Classifies each instance as work or personal and reports the source in chronological sections.",
-      "disabled": true,
-      "extract": true,
-      "has_extraction": true,
-      "key": "media",
-      "source": "system",
-      "title": "Media Consumption"
-    },
-    {
-      "app": null,
-      "description": "Reviews the day's transcript to capture each significant file or attachment that was opened, saved or shared. Generates a Markdown timeline with context about how the file was used.",
-      "disabled": true,
-      "extract": true,
-      "has_extraction": true,
-      "key": "files",
-      "source": "system",
-      "title": "File Interactions"
-    },
-    {
-      "app": null,
-      "description": "Scans conversations and tasks for sparks of new ideas, problem statements and potential ventures. Outputs a list of the most promising opportunities with context and suggested next steps.",
-      "disabled": true,
-      "extract": true,
-      "has_extraction": true,
-      "key": "opportunities",
-      "source": "system",
-      "title": "Innovation Opportunities"
-    },
-    {
-      "app": null,
       "description": "Summarizes the overall flow of the workday. Looks for patterns in focus, energy, context switching and highlights productivity insights in a Markdown report.",
       "disabled": false,
       "extract": true,
···
   "segment": [
     {
       "app": null,
-      "description": "Classifies segment activity into relevant facets based on other segment outputs",
-      "disabled": true,
-      "extract": null,
-      "has_extraction": false,
-      "key": "facets",
-      "source": "system",
-      "title": "Facet Classification"
-    },
-    {
-      "app": null,
       "description": "Creates a detailed documentary record of screen activity. Focuses on the 'what' - chronological account with preserved details, excerpts, and entities.",
       "disabled": false,
       "extract": null,
···
     },
     {
       "app": null,
-      "description": "Detects completed activities across all facets and writes records with synthesized descriptions",
-      "disabled": true,
-      "extract": null,
-      "has_extraction": false,
-      "key": "activities",
-      "source": "system",
-      "title": "Activity Records"
-    },
-    {
-      "app": null,
-      "description": "Detects configured activities present in segment and tracks state across segments",
-      "disabled": true,
-      "extract": null,
-      "has_extraction": false,
-      "key": "activity_state",
-      "source": "system",
-      "title": "Activity State"
-    },
-    {
-      "app": null,
-      "description": "Detects meetings in the segment and extracts participant names from screen and conversation.",
-      "disabled": true,
-      "extract": null,
-      "has_extraction": false,
-      "key": "speakers",
-      "source": "system",
-      "title": "Meeting Speakers"
-    },
-    {
-      "app": null,
       "description": "Extracts patterns from segment data during onboarding observation",
       "disabled": false,
       "extract": null,
···
       "key": "firstday_checkin",
       "source": "system",
       "title": "First-Day Check-In"
-    },
-    {
-      "app": null,
-      "description": "Synthesizes segment activity from content, focusing on observable changes and searchability.",
-      "disabled": true,
-      "extract": null,
-      "has_extraction": false,
-      "key": "activity",
-      "source": "system",
-      "title": "Activity Synthesis"
     },
     {
       "app": null,

tests/baselines/api/settings/providers.json

···
       "tier": 2,
       "type": "cogitate"
     },
-    "muse.system.activities": {
-      "disabled": true,
-      "group": "Think",
-      "label": "Activity Records",
-      "schedule": "segment",
-      "tier": 3,
-      "type": "generate"
-    },
-    "muse.system.activity": {
-      "disabled": true,
-      "group": "Think",
-      "label": "Activity Synthesis",
-      "schedule": "segment",
-      "tier": 2,
-      "type": "generate"
-    },
-    "muse.system.activity_state": {
-      "disabled": true,
-      "group": "Think",
-      "label": "Activity State",
-      "schedule": "segment",
-      "tier": 3,
-      "type": "generate"
-    },
     "muse.system.anticipation": {
       "disabled": false,
       "group": "Think",
···
       "tier": 2,
       "type": "generate"
     },
-    "muse.system.documentation": {
-      "disabled": true,
-      "extract": true,
-      "group": "Think",
-      "label": "Documentation Moments",
-      "schedule": "daily",
-      "tier": 2,
-      "type": "generate"
-    },
     "muse.system.entities": {
       "disabled": false,
       "group": "Think",
···
       "tier": 3,
       "type": "cogitate"
     },
-    "muse.system.facets": {
-      "disabled": true,
-      "group": "Think",
-      "label": "Facet Classification",
-      "schedule": "segment",
-      "tier": 3,
-      "type": "generate"
-    },
-    "muse.system.files": {
-      "disabled": true,
-      "extract": true,
-      "group": "Think",
-      "label": "File Interactions",
-      "schedule": "daily",
-      "tier": 2,
-      "type": "generate"
-    },
     "muse.system.firstday_checkin": {
       "disabled": false,
       "group": "Think",
···
       "extract": true,
       "group": "Think",
       "label": "Knowledge Graph",
-      "schedule": "daily",
-      "tier": 2,
-      "type": "generate"
-    },
-    "muse.system.media": {
-      "disabled": true,
-      "extract": true,
-      "group": "Think",
-      "label": "Media Consumption",
       "schedule": "daily",
       "tier": 2,
       "type": "generate"
···
       "tier": 2,
       "type": "cogitate"
     },
-    "muse.system.opportunities": {
-      "disabled": true,
-      "extract": true,
-      "group": "Think",
-      "label": "Innovation Opportunities",
-      "schedule": "daily",
-      "tier": 2,
-      "type": "generate"
-    },
     "muse.system.pulse": {
       "disabled": false,
       "group": "Think",
···
       "tier": 3,
       "type": "cogitate"
     },
-    "muse.system.research": {
-      "disabled": true,
-      "extract": true,
-      "group": "Think",
-      "label": "Research Needs",
-      "schedule": "daily",
-      "tier": 2,
-      "type": "generate"
-    },
     "muse.system.routine": {
       "disabled": false,
       "group": "Think",
···
       "tier": 2,
       "type": "generate"
     },
-    "muse.system.speakers": {
-      "disabled": true,
-      "group": "Think",
-      "label": "Meeting Speakers",
-      "schedule": "segment",
-      "tier": 2,
-      "type": "generate"
-    },
     "muse.system.timeline": {
       "disabled": false,
       "extract": true,
       "group": "Think",
       "label": "Day Timeline",
-      "schedule": "daily",
-      "tier": 2,
-      "type": "generate"
-    },
-    "muse.system.tools": {
-      "disabled": true,
-      "extract": true,
-      "group": "Think",
-      "label": "Tool Usage",
       "schedule": "daily",
       "tier": 2,
       "type": "generate"

tests/test_generate_scan_day.py

···
 
     info = mod.scan_day("20240101")
     assert "agents/flow.md" in info["processed"]
-    assert "agents/media.md" in info["repairable"]
+    assert "agents/timeline.md" in info["repairable"]
 
-    (day_dir / "agents" / "media.md").write_text("done")
+    (day_dir / "agents" / "timeline.md").write_text("done")
     info_after = mod.scan_day("20240101")
-    assert "agents/media.md" in info_after["processed"]
-    assert "agents/media.md" not in info_after["repairable"]
+    assert "agents/timeline.md" in info_after["processed"]
+    assert "agents/timeline.md" not in info_after["repairable"]

tests/test_generators.py

···
     )
 
     # Should have at least as many with disabled included
-    # (files.md, media.md, tools.md are disabled by default)
     assert len(with_disabled) >= len(without_disabled)
 
 

tests/test_muse_cli.py

···
     """All configs include known system prompts."""
     configs = _collect_configs(include_disabled=True)
     assert "flow" in configs
-    assert "activity" in configs
+    assert "sense" in configs
     assert "unified" in configs
 
 
···
     """Disabled prompts are excluded unless include_disabled is set."""
     without = _collect_configs(include_disabled=False)
     with_disabled = _collect_configs(include_disabled=True)
+    # include_disabled should return at least as many configs
     assert len(with_disabled) >= len(without)
-
-    # files.md is disabled by default
-    disabled_keys = set(with_disabled.keys()) - set(without.keys())
-    assert len(disabled_keys) > 0
+    # currently no agents are disabled (segment agents absorbed by sense,
+    # daily agents cleaned up) — both sets should be equal
+    assert len(with_disabled) == len(without)
 
 
 def test_collect_configs_filter_schedule():
···
 
 
 def test_list_prompts_disabled_shown(capsys):
-    """--disabled includes disabled prompts."""
+    """--disabled includes disabled prompts (currently none after cleanup)."""
     list_prompts(include_disabled=True)
     output = capsys.readouterr().out
 
-    # files.md is disabled, should appear
-    assert "files" in output
+    # all agents should appear in the listing
+    assert "flow" in output
 
 
 def test_show_prompt_known(capsys):
···
     records = [json.loads(x) for x in output.strip().splitlines() if x.strip()]
     files = {r["file"] for r in records}
     assert any("flow.md" in f for f in files)
-    assert any("activity.md" in f for f in files)
+    assert any("sense.md" in f for f in files)
 
     # Check a specific record has expected fields
     flow = next(r for r in records if "flow.md" in r["file"])
···
     from think.muse_cli import show_prompt_context
 
     with pytest.raises(SystemExit):
-        show_prompt_context("activity", day="20260101")
+        show_prompt_context("screen", day="20260101")
 
     output = capsys.readouterr().err
     assert "segment-scheduled" in output.lower()