@hailer/mcp 1.1.12 → 1.1.14

package/.claude/commands/help:skills.md

@@ -1,93 +0,0 @@
----
-description: Skills reference for Hailer MCP
----
-
-# Skills Reference
-
-Display skills reference to the user.
-
-## Output
-
-```
-╭─────────────────────────────────────────╮
-│     HAILER MCP - SKILLS REFERENCE       │
-╰─────────────────────────────────────────╯
-
-Skills are reusable knowledge files (.claude/skills/<name>/SKILL.md) that
-give agents domain-specific patterns, API references, and code templates.
-
-HOW SKILLS WORK:
-
-  Auto-injected: Agents declare skills in their frontmatter. The
-  SubagentStart hook injects them automatically when the agent spawns.
-
-  On-demand: The orchestrator tells an agent to load a skill via the
-  Skill tool. Only 6 agents have it: Giuseppe, Helga, Viktor,
-  Alejandro, Ingrid, Ada.
-
-─────────────────────────────────────────────────────────────────────────
-
-SDK SKILLS (core patterns):
-  SDK-activity-patterns    - Field value formats, dates, users, links
-  SDK-document-templates   - PDF/CSV template structure + generation
-  SDK-function-fields      - Calculated fields in Hailer workflows
-  SDK-generate-skill       - TypeScript type generation from workspace
-  SDK-init-skill           - Initialize new Hailer SDK projects
-  SDK-insight-queries      - SQL query patterns for insights
-  SDK-ws-config-skill      - Workflow config: fields, phases, schemas
-
-HAILER PLATFORM SKILLS:
-  hailer-activity-mover    - Phase cascade microservice patterns
-  hailer-api-client        - @hailer/cli auth, requests, signals
-  hailer-app-builder       - Build apps with @hailer/app-sdk
-  hailer-apps-pictures     - Fetch and display images from Hailer
-  hailer-design-system     - Chakra UI theme, colors, icons, components
-  hailer-monolith-automations - Webhooks, scheduled jobs in monolith
-  hailer-permissions-system - Users, teams, access control
-  hailer-project-protocol  - Full SDK workflow reference
-  hailer-rest-api          - Direct HTTP API endpoints
-
-INTEGRATION SKILLS:
-  integration-patterns     - Activity movers, webhooks, SCIM, Kafka
-  zapier-hailer-patterns   - Zapier triggers, actions, Zap configs
-  insight-join-patterns    - JOIN syntax for cross-workflow insights
-
-TOOL & AGENT SKILLS:
-  agent-structure          - Template for creating new agents
-  delegation-routing       - Full routing table + chaining patterns
-  tool-builder             - Building MCP tools for Hailer server
-  mcp-direct-tools         - MCP tools not assigned to agents
-
-QUALITY & FIX SKILLS (auto-loaded on errors):
-  tool-parameter-usage     - Extract IDs, correct parameter formats
-  tool-response-verification - Verify MCP results before reporting
-  optional-parameters      - Omit optional params vs empty values
-  json-only-output         - Fix agents adding prose after JSON
-  testing-patterns         - vitest, playwright, build verification
-
-REFERENCE SKILLS:
-  api-documentation-patterns - API doc standards for Marcus
-  chrome-mcp-reference     - Browser automation reference
-  frontend-design          - UI design patterns
-  lsp-setup                - Language Server Protocol setup
-  publish-hailer-app       - App publishing to production
-
-─────────────────────────────────────────────────────────────────────────
-
-ON-DEMAND SKILL LOADING (tell the orchestrator):
-
-  "Load hailer-apps-pictures for Giuseppe"
-  → Giuseppe gets image handling patterns
-
-  "Viktor needs insight-join-patterns for this query"
-  → Viktor gets JOIN syntax for cross-workflow data
-
-  Only works with: Giuseppe, Helga, Viktor, Alejandro, Ingrid, Ada
-
-─────────────────────────────────────────────────────────────────────────
-
-SEE ALSO:
-  /help agents   - Which agents use which skills
-  /help commands - All slash commands
-  /help tools    - MCP tools reference
-```

package/.claude/commands/help:tools.md

@@ -1,75 +0,0 @@
----
-description: MCP tools reference for Hailer MCP
----
-
-# MCP Tools Reference
-
-Display MCP tools reference to the user.
-
-## Output
-
-```
-╭─────────────────────────────────────────╮
-│      HAILER MCP - TOOLS REFERENCE       │
-╰─────────────────────────────────────────╯
-
-MCP tools provide direct access to Hailer APIs. These are used by
-agents but can also be called directly.
-
-WORKFLOW TOOLS:
-  list_workflows          - List all workflows in workspace
-  list_workflows_minimal  - Compact workflow list with counts
-  list_workflow_phases    - Get phases for a workflow
-  get_workflow_schema     - Get field definitions for a workflow
-  install_workflow        - Create workflow from template
-
-ACTIVITY TOOLS:
-  list_activities         - List activities in a workflow phase
-  show_activity_by_id     - Get single activity details
-  create_activity         - Create new activity (single or bulk)
-  update_activity         - Update activity (single or bulk)
-  count_activities        - Count activities in workflow
-
-DISCUSSION TOOLS:
-  list_my_discussions        - List discussions you're in
-  fetch_discussion_messages  - Read messages from discussion
-  add_discussion_message     - Post to a discussion
-  join_discussion            - Join a discussion
-  leave_discussion           - Leave a discussion
-  invite_discussion_members  - Invite users to discussion
-
-INSIGHT TOOLS:
-  list_insights      - List all insights
-  create_insight     - Create SQL-like insight
-  preview_insight    - Test insight query
-  get_insight_data   - Execute insight and get results
-  update_insight     - Modify existing insight
-
-APP TOOLS:
-  list_apps              - List apps in workspace
-  create_app             - Create app entry
-  update_app             - Update app properties
-  scaffold_hailer_app    - Generate app from template
-  publish_hailer_app     - Deploy app to production
-
-FILE TOOLS:
-  upload_files     - Upload files to Hailer
-  download_file    - Download file from Hailer
-
-USER TOOLS:
-  search_workspace_users - Find users by name
-
-TEMPLATE TOOLS:
-  list_templates     - List marketplace templates
-  get_template       - Get template details
-  install_template   - Install template to workspace
-  publish_template   - Publish workspace as template
-
-USAGE:
-  Tools are called via the MCP protocol. The orchestrator and
-  agents use them automatically based on your requests.
-
-SEE ALSO:
-  /help agents   - How agents use these tools
-  /help commands - Slash commands available
-```

package/.claude/commands/hotfix-squad.md

@@ -1,112 +0,0 @@
----
-description: Quick bug fix with Tanya, Simple Writer, and Svetlana
-argument-hint: "bug description"
-allowed-tools: Task, Bash
----
-# Hotfix Squad
-
-Sequential pipeline with iterative loop: Reproduce bug, apply fix, verify, review. Loops back if review fails.
-
-**Agents:**
-1. **Tanya** - Test runner (create failing test, verify fix)
-2. **Simple Writer** - Code editor (apply minimal fix)
-3. **Svetlana** - Code review (security audit of the fix)
-
-**Goal:** $ARGUMENTS
-
-## Protocol
-
-### Step 1: Tanya (Reproduce Bug)
-
-Spawn Tanya to create a test that demonstrates the bug:
-
-```
-Task(subagent_type="agent-tanya-test-runner", prompt="Create a test that reproduces this bug: $ARGUMENTS.\n\nThe test should:\n- Fail with the current code (red)\n- Clearly demonstrate the bug\n- Be minimal and focused\n\nDo NOT fix the bug yet. Just create the failing test and report the failure.")
-```
-
-Wait for result. The test should be failing (RED state).
-
-### Step 2: Fix-Verify-Review Loop
-
-Track iteration count. Max **3 iterations** before escalating to user with remaining issues.
-
-**Set:** `iteration = 1`
-
-#### Step 2a: Simple Writer (Apply Fix)
-
-Spawn Simple Writer with accumulated context from all previous iterations:
-
-```
-Task(subagent_type="agent-simple-writer", prompt="Fix the bug in: $ARGUMENTS.\n\nContext:\nTanya created a failing test that reproduces the bug:\n[PASTE TANYA'S TEST CODE AND FAILURE OUTPUT]\n\n[IF iteration > 1: Include ALL accumulated feedback:\n- Tanya's latest test results (pass/fail details)\n- Svetlana's review feedback (if review was reached in previous iteration)\n- What was already tried and why it didn't fully work\nThis prevents repeating previous mistakes.]\n\nMake the MINIMAL change needed to make the test pass (GREEN state). Do not refactor or improve surrounding code.")
-```
-
-#### Step 2b: Tanya (Verify Fix)
-
-Run the test to confirm the fix works:
-
-```
-Task(subagent_type="agent-tanya-test-runner", prompt="Re-run the test for: $ARGUMENTS. Confirm it now passes with Simple Writer's fix. Also run any related tests to check for regressions.")
-```
-
-If tests FAIL:
-- If `iteration < 3`: increment iteration, go back to **Step 2a** with the test failure output
-- If `iteration >= 3`: escalate to user (see Step 3)
-
-#### Step 2c: Svetlana (Security Review)
-
-Tests passed. Spawn Svetlana to audit the fix:
-
-```
-Task(subagent_type="agent-svetlana-code-review", prompt="Security review of the hotfix for: $ARGUMENTS.\n\nFix applied by Simple Writer:\n[PASTE SIMPLE WRITER'S CHANGES]\n\nIteration: [iteration] of 3\n\nCheck for:\n- Security vulnerabilities\n- Data validation issues\n- Authentication/authorization concerns\n- Edge cases that could be exploited\n\nReturn verdict: APPROVED or REQUEST_CHANGES with specific issues to fix.")
-```
-
-**If APPROVED:** proceed to Step 3 (report).
-
-**If REQUEST_CHANGES:**
-- If `iteration < 3`: increment iteration, go back to **Step 2a** with Svetlana's feedback
-- If `iteration >= 3`: escalate to user (see Step 3)
-
-### Step 3: Report
-
-```markdown
-## Hotfix Squad Complete
-
-### Loop Summary
-- Iterations: [count] of 3 max
-- Final status: FIXED / ESCALATED
-
-### Tanya (Test)
-- Bug reproduced: YES
-- Test status before fix: FAILED
-- Test status after fix: PASSED / STILL FAILING
-- Regressions found: [yes/no]
-
-### Simple Writer (Fix)
-- Files modified: [list]
-- Lines changed: [count]
-- Approach: [brief description]
-
-### Svetlana (Security)
-- Verdict: APPROVED / REQUEST_CHANGES
-- Critical issues: [count]
-- Warnings: [count]
-- [If REQUEST_CHANGES: list remaining issues]
-
-### Next Steps
-[If FIXED:]
-- Deploy to staging
-- Monitor error logs
-
-[If ESCALATED after 3 iterations:]
-- Manual intervention needed
-- Remaining issues: [list from Svetlana/Tanya]
-- Attempted fixes: [summary of what was tried]
-```
-
-## Notes
-
-- RED -> GREEN -> REVIEW loop ensures quality
-- Fix must be minimal - no refactoring
-- Max 3 iterations prevents infinite loops
-- Each iteration passes previous feedback to Simple Writer so it doesn't repeat mistakes
-- Security check is mandatory before reporting success

package/.claude/commands/integration-squad.md

@@ -1,82 +0,0 @@
----
-description: Build backend integrations with Kenji, Ivan, and Tanya
-argument-hint: "integration description"
-allowed-tools: Task, Bash, Read
----
-# Integration Squad
-
-Sequential pipeline: Schema discovery, build integration, then verify with tests.
-
-**Agents:**
-1. **Kenji** - Schema discovery (workflow fields, types, IDs)
-2. **Ivan** - Build integration (monolith webhooks, scheduled jobs, automations)
-3. **Tanya** - Test runner (verify integration with tests)
-
-**Goal:** $ARGUMENTS
-
-## Protocol
-
-### Step 1: Kenji (Schema Discovery)
-
-Start with Kenji to gather workflow schema and field IDs needed for the integration:
-
-```
-Task(subagent_type="agent-kenji-data-reader", prompt="List all workflows and their fields relevant to: $ARGUMENTS. Include field IDs, types, and any existing integrations. Also identify webhook URLs and activity phase names needed.")
-```
-
-Wait for result. Save the schema output - Ivan needs these IDs.
-
-### Step 2: Ivan (Build Integration)
-
-Spawn Ivan with the schema context from Kenji:
-
-```
-Task(subagent_type="agent-ivan-monolith", prompt="Build a backend integration for: $ARGUMENTS.\n\nWorkflow schema from Kenji:\n[PASTE KENJI'S OUTPUT - workflow IDs, field IDs, types, phases]\n\nImplement in the hailer-integration monolith. Use correct IDs for webhooks, scheduled jobs, or automations.")
-```
-
-Wait for result. If `"status": "ready_to_push"`:
-- Run the push commands Ivan provides
-
-### Step 3: Tanya (Test Runner)
-
-Spawn Tanya to verify the integration works:
-
-```
-Task(subagent_type="agent-tanya-test-runner", prompt="Test the integration for: $ARGUMENTS.\n\nTest coverage needed:\n- Webhook payload validation (if webhook)\n- Scheduled job execution (if scheduled)\n- Activity creation/phase transitions\n- Error handling and edge cases\n\nRun tests and report pass/fail counts.")
-```
-
-Wait for result. If tests fail, report which ones and offer to have Ivan fix issues.
-
-### Step 4: Report
-
-```markdown
-## Integration Squad Complete
-
-### Kenji (Schema Discovery)
-- Workflows found: [list]
-- Fields mapped: [count]
-- Phases identified: [list]
-- Existing integrations: [list or "none"]
-
-### Ivan (Monolith Integration)
-- Integration type: [webhook/scheduled/automation]
-- Files created/modified: [list]
-- Endpoints: [list if webhook]
-- Commands run: [list]
-
-### Tanya (Tests)
-- Tests: X passed, X failed
-- Build: Pass/Fail
-- [Failed test details if any]
-
-### Next Steps
-- Deploy to staging environment
-- Test end-to-end in Hailer
-- Monitor for errors in production logs
-```
-
-## Notes
-
-- Kenji must run first to get real IDs - never let Ivan guess IDs
-- Each agent in the pipeline depends on output from the previous step
-- If tests fail, Ivan may need to revise the integration code

package/.claude/commands/janitor-squad.md

@@ -1,167 +0,0 @@
----
-description: Deep project cleanup - code, config, and data patterns
-argument-hint: [scope or blank for full project]
-allowed-tools: Task, Bash
----
-# Janitor Squad
-
-Deep project cleanup across code, configuration, and data. Discovers dead patterns and auto-fixes clear-cut removals.
-
-**Agents:**
-- **Lars** - Dead code detection (unused imports, unreachable code, type errors via LSP)
-- **Bjorn** - Configuration audit (deprecated fields, broken references, unused workflows)
-- **Viktor** - Data analysis (unpopulated fields, zero-activity workflows, silent insights)
-- **Simple Writer** - Auto-fix confirmed dead code and unused imports (fix loop)
-- **Code Simplifier** - Simplify complex code blocks identified during discovery (fix loop)
-
-**Target:** $ARGUMENTS (if blank, scan full project)
-
-**Changed files:** Orchestrator runs `git diff --name-only HEAD` to scope if needed.
-
-## Protocol
-
-### Step 1: Determine Scope
-
-If `$ARGUMENTS` has specific files/directories, use those as the target.
-Otherwise, scan the entire project.
-
-If `$ARGUMENTS` contains `--code-only`:
-- Skip Bjorn and Viktor
-- Only run Lars in discovery phase
-
-If `$ARGUMENTS` contains `--config-only`:
-- Skip Lars and Viktor
-- Only run Bjorn in discovery phase
-
-If `$ARGUMENTS` contains `--report-only`:
-- Skip all fix loop iterations
-- Report findings only (no auto-fixes)
-
-### Step 2: Launch Discovery Agents in Parallel
-
-**Set:** `iteration = 1`
-
-Spawn all three discovery agents simultaneously using multiple Task tool calls in a single message:
-
-**Lars:**
-```
-Task(subagent_type="agent-lars-code-inspector", prompt="Inspect the project for dead code patterns: [TARGET]. Find:\n- Unused imports\n- Unreachable code blocks\n- Unused variables and functions\n- Type errors\n\nUse LSP if available, fall back to tsc/eslint. Return detailed findings grouped by file.")
-```
-
-**Bjorn:**
-```
-Task(subagent_type="agent-bjorn-config-audit", prompt="Audit workspace configuration for zombie patterns: [TARGET]. Check:\n- Deprecated fields in workspace/fields.ts\n- Broken field references in phases\n- Unused workflows (defined but zero activities)\n- Broken enum references\n- Orphaned configuration entries\n\nReturn issues grouped by category with severity.")
-```
-
-**Viktor:**
-```
-Task(subagent_type="agent-viktor-sql-insights", prompt="Analyze data patterns in workflows: [TARGET]. Find:\n- Fields that are defined but never populated (zero values across all activities)\n- Workflows with zero activities (created but unused)\n- Insights that return empty data (broken or obsolete)\n- Calculated fields that never execute\n- Orphaned data patterns\n\nReturn findings with field IDs, workflow IDs, and impact estimates.")
-```
-
-### Step 3: Categorize Findings
-
-Collect results from all three agents. Categorize each finding as:
-
-**AUTO-FIXABLE** (Simple Writer can safely remove):
-- Unused imports identified by Lars
-- Dead code blocks with no side effects
-- Workflow definitions with zero activities (from Viktor + Bjorn)
-- Deprecated enum references (from Bjorn)
-- Never-populated fields that can be safely archived (from Viktor + Bjorn)
-
-**NEEDS-HUMAN-REVIEW** (escalate to user):
-- Architecture concerns
-- Fields that are rarely used but intentional
-- Complex logic entangled with dead code
-- Data cleanup that affects reporting history
-- Performance optimizations requiring design changes
-
-### Step 4: Auto-Fix Loop (if auto-fixable items found AND `--report-only` not set AND `iteration < 3`)
-
-If critical auto-fixable items exist, spawn two agents to clean up. If Simple Writer's fixes introduce new issues detected by re-audit, escalate remaining issues to user after max 2 iterations.
-
-**Simple Writer:**
-```
-Task(subagent_type="agent-simple-writer", prompt="Remove confirmed dead code and unused imports from the project:\n\n[LIST AUTO-FIXABLE ITEMS WITH FILE PATHS AND LINE NUMBERS]\n\nFrom Lars:\n- [Unused imports with files]\n- [Dead code blocks with files]\n\nFrom Bjorn:\n- [Deprecated enum references with files]\n- [Unused workflow definitions with IDs]\n\nFrom Viktor:\n- [Never-populated field definitions with IDs]\n\nApply minimal removals only. Do not refactor or improve beyond confirmed dead patterns.")
-```
-
-**Code Simplifier:**
-```
-Task(subagent_type="agent-code-simplifier", prompt="After dead code removal, simplify complex code blocks identified as difficult to maintain: [TARGET].\n\nFocus on:\n- Variable naming clarity\n- Function complexity reduction\n- Comment clarity around remaining logic\n- Code organization in affected files\n\nReturn refactoring suggestions with before/after examples.")
-```
-
-After both finish:
-- Increment `iteration`
-- Go back to **Step 2** to re-run all discovery agents
-- On re-discovery, tell agents to verify previous issues are resolved
-- Max 2 re-check iterations (3 total discovery runs)
-
-### Step 5: Report
-
-```markdown
-## Janitor Squad Report
-
-### Loop Summary
-- Discovery iterations: [count]
-- Auto-fixes applied: [yes/no]
-- Items removed: [count by category]
-
-### Lars (Dead Code Detection)
-- Unused imports: X (Y auto-removed)
-- Dead code blocks: X (Y auto-removed)
-- Type errors: X
-- [Remaining issues grouped by file]
-
-### Bjorn (Config Audit)
-- Deprecated fields: X
-- Broken references: X (Y auto-removed)
-- Unused workflows: X (Y auto-removed)
-- Orphaned config: X
-- [Remaining issues grouped by category]
-
-### Viktor (Data Analysis)
-- Never-populated fields: X (Y marked for archival)
-- Zero-activity workflows: X (Y removed)
-- Silent insights: X
-- Orphaned data patterns: X
-- [Remaining items grouped by workflow]
-
-### Auto-Fixes Applied
-[If any fixes were made:]
-- [File/ID]: [what was removed/archived]
-- [File/ID]: [what was removed/archived]
-
-### Remaining Issues (Manual Action Needed)
-[Issues that require human review]
-- [Category]: [Details]
-
-### Recommended Cleanup Order
-1. [Remove these orphaned items first]
-2. [Archive these fields next]
-3. [Review these design concerns]
-
-### Summary
-[Overall health assessment]
-[Estimated time to apply remaining cleanup]
-```
-
-If any agent fails or times out, report partial results from successful agents, note which failed, and offer to re-run individually.
-
-## Options
-
-| Flag | Effect |
-|------|--------|
-| `--code-only` | Skip Bjorn and Viktor, just code cleanup via Lars |
-| `--config-only` | Skip Lars and Viktor, just workspace config audit via Bjorn |
-| `--report-only` | Report findings only, no auto-fix loop (discovery phase only) |
-| `--bg` | Run all discovery agents in background mode |
-
-If `--bg` is present, launch all discovery agents with `run_in_background: true` and tell the user they'll be notified when discovery is complete, then proceed with fix loop when they're ready.
-
-## Notes
-
-- Max 2 re-discovery iterations (3 total) to prevent infinite loops
-- Simple Writer only removes clear-cut dead code - ambiguous items go to user review
-- Data cleanup (Viktor findings) may affect reports/history - always prompt user before removal
-- Each re-discovery is a full parallel sweep across all enabled agents
-- The `--report-only` flag gives discovery results without auto-fixes

package/.claude/commands/learn-auto.md

@@ -1,120 +0,0 @@
----
-description: Scan conversation for learnings and capture to inbox
-argument-hint: [optional focus area]
----
-# Auto-Learn
-
-Scan conversation for potential learnings, present for confirmation, write to inbox.
-
-## Trigger Patterns
-
-Scan conversation for these signals:
-
-### 1. Error → Fix Sequences
-```
-Pattern: Error/failure message followed by successful resolution
-Signal: "Error:", "failed", "doesn't work" → later "fixed", "working now", "solved"
-Extract: What was wrong, what fixed it
-```
-
-### 2. User Corrections
-```
-Pattern: User corrects agent output or approach
-Signal: "No, it should be...", "Actually, use...", "That's wrong, do..."
-Extract: Wrong approach, correct approach
-```
-
-### 3. Explicit Learning Signals
-```
-Pattern: User explicitly notes something important
-Signal: "Good to know", "I'll remember that", "Important:", "Note to self"
-Extract: The insight
-```
-
-### 4. Agent Failures
-```
-Pattern: Agent returned error or wrong result
-Signal: "status": "error", validation failures, user says "that's not right"
-Extract: What failed, why, how to prevent
-```
-
-### 5. Repeated Attempts
-```
-Pattern: Same operation tried multiple times before success
-Signal: 2+ similar tool calls, retries with different parameters
-Extract: What didn't work, what finally worked
-```
-
-## Instructions
-
-### Step 1: Scan Conversation
-
-Review the conversation for patterns above. For each potential learning, note:
-- **Type**: error-fix | correction | insight | agent-failure | retry-pattern
-- **Context**: What was happening
-- **Learning**: The key takeaway
-- **Category**: agent/X | skill/X | pattern | gotcha | bug
-
-### Step 2: Present Findings
-
-If learnings found, present to user:
-
-```
-Found [N] potential learnings from this session:
-
-1. [agent/kenji] Field lookup should check enums.ts first
-   Context: Kenji made API call when data was available locally
-
-2. [pattern] Date fields from Hailer come pre-formatted
-   Context: Tried to format already-formatted date, got wrong output
-
-3. [gotcha] Push must complete before pull
-   Context: Pull overwrote local changes
-
-Confirm which to save? (all / 1,2 / none)
-```
-
-Use AskUserQuestion:
-- "Save all"
-- "Select specific (enter numbers)"
-- "Skip - nothing worth saving"
-
-### Step 3: Write to Inbox
-
-For confirmed learnings, append to `inbox.md`:
-
-```markdown
-## Pending
-
-- [<category>] <learning description> _(from: <project>, <date>, auto-learn)_
-```
-
-If in hub repo (hailer-claude-reference), write directly to `inbox.md`.
-If in project repo, write to `docs/learnings.md` or project's inbox location.
-
-### Step 4: Report
-
-```
-Captured [N] learnings to inbox:
-- [agent/kenji] Field lookup should check enums.ts first
-- [pattern] Date fields from Hailer come pre-formatted
-
-Review later with /learn to apply fixes, or let Ada auto-process.
-```
-
-## No Learnings Found
-
-If conversation has no clear learnings:
-
-```
-No obvious learnings detected in this session.
-
-To capture something manually: /learn <category> <description>
-```
-
-## Notes
-
-- This is DETECTION only - doesn't apply fixes (that's /learn or Ada's job)
-- User confirms before anything is saved
-- Bias toward false negatives (miss some) rather than false positives (noise)
-- Works best at end of session when there's context to analyze