feat: replace Teams with Skillshare-based Share system, streamline spec workflow and hooks

.github/workflows/deploy-website.yml

@@ -7,6 +7,7 @@ name: Deploy Website
       - main
     paths:
       - "docs/site/**"
+      - "docs/docusaurus/**"
       - ".github/workflows/deploy-website.yml"
   workflow_dispatch:
 

.github/workflows/release-dev.yml

@@ -31,14 +31,16 @@ jobs:
 
       - name: Run Trivy filesystem scan
         uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8 # 0.33.1
+        env:
+          TRIVY_SKIP_VERSION_CHECK: "true"
         with:
           scan-type: "fs"
           scan-ref: "."
           scanners: "vuln,secret"
           severity: "CRITICAL,HIGH"
           exit-code: "1"
           ignore-unfixed: true
-          skip-dirs: ".venv,node_modules,console/node_modules,launcher,docs/site/api,console"
+          skip-dirs: ".venv,node_modules,console/node_modules,launcher,docs/site/api,console,docs/site/node_modules,docs/docusaurus/node_modules"
           trivyignores: ".trivyignore"
           format: "table"
           output: trivy-results.txt
@@ -49,12 +51,9 @@ jobs:
           if [[ -s trivy-results.txt ]]; then
             {
               echo "### Security Scan Results"
-              echo "<details><summary>Click to expand Trivy output</summary>"
-              echo ""
               echo '```'
               cat trivy-results.txt
               echo '```'
-              echo "</details>"
             } >> $GITHUB_STEP_SUMMARY
           else
             echo "### Security Scan: No issues found" >> $GITHUB_STEP_SUMMARY

.github/workflows/release.yml

@@ -81,14 +81,16 @@ jobs:
 
       - name: Run Trivy vulnerability and secret scanner
         uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8 # 0.33.1
+        env:
+          TRIVY_SKIP_VERSION_CHECK: "true"
         with:
           scan-type: 'fs'
           scan-ref: '.'
           scanners: 'vuln,secret'
           severity: 'CRITICAL,HIGH'
           exit-code: '1'
           ignore-unfixed: true
-          skip-dirs: '.venv,node_modules,console/node_modules,launcher,docs/site/api,console'
+          skip-dirs: '.venv,node_modules,console/node_modules,launcher,docs/site/api,console,docs/site/node_modules,docs/docusaurus/node_modules'
           trivyignores: '.trivyignore'
           format: 'table'
           output: trivy-results.txt
@@ -99,12 +101,9 @@ jobs:
           if [[ -s trivy-results.txt ]]; then
             {
               echo "### Security Scan Results"
-              echo "<details><summary>Click to expand Trivy output</summary>"
-              echo ""
               echo '```'
               cat trivy-results.txt
               echo '```'
-              echo "</details>"
             } >> $GITHUB_STEP_SUMMARY
           else
             echo "### Security Scan: No issues found" >> $GITHUB_STEP_SUMMARY

.gitignore

@@ -223,7 +223,6 @@ __marimo__/
 
 # Claude Code
 CLAUDE.md
-.devcontainer
 .playwright-*/
 .vercel
 .mcp.json

docs/docusaurus/.gitignore

@@ -0,0 +1,5 @@
+node_modules/
+build/
+.docusaurus/
+.cache-loader/
+.playwright-cli/

docs/docusaurus/docs/features/context-preservation.md

@@ -0,0 +1,38 @@
+---
+sidebar_position: 3
+title: Context Preservation
+description: Seamless continuation across auto-compaction cycles
+---
+
+# Context Preservation
+
+Seamless continuation across auto-compaction cycles.
+
+Claude Code reserves ~16.5% of the context window as a compaction buffer, triggering auto-compaction at ~83.5% raw usage. Pilot hooks intercept this cycle to preserve state — you never lose progress mid-task. Multiple Pilot sessions can run in parallel on the same project without interference.
+
+## The Compaction Cycle
+
+```
+PreCompact → Compact → SessionStart(compact)
+```
+
+1. **PreCompact** — `pre_compact.py` captures active plan, task list, recent decisions, and key context to Pilot Shell Console memory.
+2. **Compact** — Claude Code auto-compaction summarizes conversation history. Preserves recent tool calls and conversation flow.
+3. **SessionStart(compact)** — `post_compact_restore.py` re-injects Pilot context: active plan path, task state, key decisions. Work resumes seamlessly.
+
+## Effective Context Display
+
+Pilot rescales the raw context usage to an **effective 0–100% range** so the status bar fills naturally to 100% right before compaction fires. A `▓` buffer indicator at the end of the bar shows the reserved zone. The context monitor warns at ~80% effective (informational) and ~90%+ effective (caution) — no confusing raw percentages.
+
+## What Gets Preserved
+
+- Active plan file path and current status (PENDING/COMPLETE/VERIFIED)
+- Task list with completion state and in-progress task
+- Key decisions made during the session
+- Recently modified files and their context
+- Error messages and debugging progress
+- Memory observations from the Pilot Shell Console
+
+:::tip Never rush due to context warnings
+Context limits are not an emergency — auto-compaction preserves everything and resumes seamlessly. Finish the current task with full quality. The only thing that matters is the output, not the context percentage.
+:::

docs/docusaurus/docs/features/hooks.md

@@ -0,0 +1,79 @@
+---
+sidebar_position: 2
+title: Hooks Pipeline
+description: 15 hooks across 7 lifecycle events — fire automatically at every stage
+---
+
+# Hooks Pipeline
+
+15 hooks across 7 lifecycle events — fire automatically at every stage.
+
+Hooks are the enforcement layer. They run at each stage of Claude's work cycle — automatically, without prompting. Blocking hooks can reject an action or force a fix. Non-blocking hooks warn without interrupting. Async hooks run in the background.
+
+## SessionStart
+
+*On startup, clear, or after compaction*
+
+| Hook | Type | Description |
+|------|------|-------------|
+| Memory loader | Blocking | Loads persistent context from Console memory into the session |
+| `post_compact_restore.py` | Blocking | Re-injects active plan, task state, and key context after compaction |
+| Session tracker | Async | Initializes user message tracking for the session |
+
+## UserPromptSubmit
+
+*When the user sends a message*
+
+| Hook | Type | Description |
+|------|------|-------------|
+| Session initializer | Async | Registers the session with the Console worker daemon on first message |
+
+## PreToolUse
+
+*Before search, web, or task tools*
+
+| Hook | Type | Description |
+|------|------|-------------|
+| `tool_redirect.py` | Blocking | Redirects to MCP alternatives, blocks plan mode conflicts, hints Probe CLI for search |
+
+## PostToolUse
+
+*After every Write / Edit / MultiEdit*
+
+| Hook | Type | Description |
+|------|------|-------------|
+| `file_checker.py` | Blocking | Python (ruff + basedpyright), TypeScript (Prettier + ESLint + tsc), Go (gofmt + golangci-lint). Auto-fixes formatting. |
+| `tdd_enforcer.py` | Non-blocking | Warns when implementation files are edited without a failing test first |
+| `context_monitor.py` | Non-blocking | Tracks context usage 0–100%. Warns at ~80%, caution at ~90%+ |
+| Memory observer | Async | Captures decisions, discoveries, and bugfixes to persistent memory |
+
+## PreCompact
+
+*Before auto-compaction fires*
+
+| Hook | Type | Description |
+|------|------|-------------|
+| `pre_compact.py` | Blocking | Snapshots active plan, task list, and key decisions to memory |
+
+## Stop
+
+*When Claude tries to finish*
+
+| Hook | Type | Description |
+|------|------|-------------|
+| `spec_stop_guard.py` | Blocking | Blocks stopping if an active spec hasn't completed verification |
+| `spec_plan_validator.py` | Blocking | Verifies plan file was created with required sections |
+| `spec_verify_validator.py` | Blocking | Verifies plan status was updated to VERIFIED |
+| Session summarizer | Async | Saves session observations to memory for future sessions |
+
+## SessionEnd
+
+*When the session closes*
+
+| Hook | Type | Description |
+|------|------|-------------|
+| `session_end.py` | Blocking | Stops worker daemon if no other sessions active. Sends dashboard notification. |
+
+:::info Closed loop
+When compaction fires, **PreCompact** captures your active plan, task list, and key decisions to persistent memory. **SessionStart** restores everything afterward — work continues exactly where it left off. No progress lost, no manual intervention.
+:::

docs/docusaurus/docs/features/model-routing.md

@@ -0,0 +1,31 @@
+---
+sidebar_position: 5
+title: Model Routing
+description: Opus where reasoning matters, Sonnet where speed and cost matter
+---
+
+# Model Routing
+
+Opus where reasoning matters, Sonnet where speed and cost matter.
+
+Pilot automatically routes each phase to the right model. Rather than always using the most powerful (and most expensive) model, it applies reasoning where reasoning has the highest impact — and uses fast, cost-effective execution where a clear spec makes quality predictable.
+
+## Routing Table
+
+| Phase | Model | Rationale |
+|-------|-------|-----------|
+| **Planning** | Opus | Exploring your codebase, designing architecture, and writing the spec requires deep reasoning. A good plan is the foundation — invest here. |
+| **Plan Verification** | Sonnet | The plan-reviewer sub-agent validates completeness and challenges assumptions on every feature spec. |
+| **Implementation** | Sonnet | With a solid plan, writing code is straightforward. Sonnet is fast, cost-effective, and produces high-quality code when guided by a clear spec and strong hooks. |
+| **Code Verification** | Sonnet | The unified spec-reviewer agent handles deep code review (compliance + quality + goal). The orchestrator runs mechanical checks and applies fixes efficiently. |
+
+## The Insight
+
+- Implementation is the easy part when the plan is good and verification is thorough
+- Pilot invests reasoning power (Opus) where it has the highest impact: planning
+- Sonnet handles implementation and verification — guided by a solid plan and structured review agents
+- The result: better output at lower cost than running Opus everywhere
+
+:::tip Fully configurable
+Configure via the Pilot Shell Console Settings tab (`localhost:41777/#/settings`). Choose between Sonnet 4.6 and Opus 4.6 for the main session, each command, and each sub-agent independently. Enable the **Extended Context (1M)** toggle to switch all models to the 1M token context window simultaneously — useful for very large codebases. Requires Max 20x or Enterprise subscription.
+:::

docs/docusaurus/docs/features/rules.md

@@ -0,0 +1,53 @@
+---
+sidebar_position: 4
+title: Rules & Standards
+description: Production-tested best practices loaded into every session
+---
+
+# Rules & Standards
+
+Production-tested best practices loaded into every session.
+
+Rules are loaded automatically at session start. They're not suggestions — they're enforced standards. Coding standards load conditionally based on the file type being edited, keeping context lean. Your project-level rules in `.claude/rules/` are loaded alongside Pilot's built-ins and take precedence when they overlap.
+
+## Built-in Rule Categories
+
+### Core Workflow (3 rules)
+
+- `task-and-workflow.md` — Task management, /spec orchestration, deviation handling
+- `testing.md` — TDD workflow, test strategy, coverage requirements (≥80%)
+- `verification.md` — Execution verification, completion requirements
+
+### Development Practices (3 rules)
+
+- `development-practices.md` — Project policies, systematic debugging, git rules
+- `context-management.md` — Auto-compaction and context preservation
+- `pilot-memory.md` — Online learning triggers
+
+### Tools (3 rules)
+
+- `research-tools.md` — Search priority and tool selection guide
+- `cli-tools.md` — Pilot CLI, Probe code search
+- `playwright-cli.md` — Browser automation for E2E UI testing
+
+### Collaboration (1 rule)
+
+- `skill-sharing.md` — Skillshare CLI and three-tier sharing model
+
+## Coding Standards — Activated by File Type
+
+| Standard | Activates On | Coverage |
+|----------|-------------|----------|
+| Python | `*.py` | uv, pytest, ruff, basedpyright, type hints |
+| TypeScript | `*.ts, *.tsx, *.js, *.jsx` | npm/pnpm, Jest, ESLint, Prettier, React patterns |
+| Go | `*.go` | Modules, testing, formatting, error handling |
+| Frontend | `*.tsx, *.jsx, *.html, *.vue, *.css` | Components, CSS, accessibility, responsive design |
+| Backend | `**/models/**, **/routes/**, **/api/**` | API design, data models, query optimization, migrations |
+
+:::tip Custom rules
+Create `.claude/rules/my-rule.md` in your project. Add `paths: ["*.py"]` frontmatter to activate only for specific file types. Run `/sync` to auto-discover patterns and generate project-specific rules for you.
+:::
+
+:::info Monorepo support
+Organize rules in nested subdirectories by product and team (e.g. `.claude/rules/my-product/team-x/`). Team-level rules must use `paths` frontmatter to scope to the right files. `/sync` generates a `README.md` in your rules directory to document the structure.
+:::