thumbgate 1.16.22 → 1.18.0

package/.claude-plugin/marketplace.json

@@ -1,6 +1,6 @@
 {
   "name": "thumbgate-marketplace",
-  "version": "1.16.22",
+  "version": "1.18.0",
   "owner": {
     "name": "Igor Ganapolsky",
     "email": "ig5973700@gmail.com"
@@ -13,7 +13,7 @@
         "source": "npm",
         "package": "thumbgate"
       },
-      "version": "1.16.22",
+      "version": "1.18.0",
       "author": {
         "name": "Igor Ganapolsky"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "thumbgate",
   "description": "Type 👍 or 👎 on any agent action. ThumbGate captures it, distills a lesson, and blocks the pattern from repeating. One thumbs-down = the agent physically cannot make that mistake again. 33 pre-action checks, budget enforcement, self-protection, and NIST/SOC2 compliance tags.",
-  "version": "1.16.22",
+  "version": "1.18.0",
   "author": {
     "name": "Igor Ganapolsky"
   },

package/.well-known/llms.txt

@@ -40,7 +40,7 @@ npx thumbgate init --agent claude-code
 ## Pricing
 
 - Free GPT: advice, checkpointing, and setup help in ChatGPT
-- Free local CLI: 3 feedback captures/day, 5 lesson searches/day, recall, and local Pre-Action Checks after install
+- Free local CLI: unlimited feedback captures, up to 5 active prevention rules, and local Pre-Action Checks after install (recall and lesson search are Pro-only)
 - Pro: $19/mo or $149/yr — personal enforcement proof, local dashboard, check debugger, DPO export, and review-ready exports
 - Team: $49/seat/mo, 3-seat minimum after intake — shared lessons, org visibility, approval boundaries, and rollout proof
 

package/.well-known/mcp/server-card.json

@@ -1,6 +1,6 @@
 {
   "name": "thumbgate",
-  "version": "1.16.22",
+  "version": "1.18.0",
   "description": "ThumbGate — 👍👎 feedback that teaches your AI agent. Thumbs down a mistake, it never happens again.",
   "homepage": "https://thumbgate-production.up.railway.app",
   "transport": "stdio",

package/README.md

@@ -146,6 +146,9 @@ Each recommendation ships with the benchmark commands to run next: feedback-deri
 |-------|---------|
 | **Claude Code** | `npx thumbgate init --agent claude-code` |
 | **Cursor** | `npx thumbgate init --agent cursor` |
+| **VS Code / Open VSX** | [plugins/vscode-extension/README.md](plugins/vscode-extension/README.md) |
+| **Antigravity-compatible** | [plugins/antigravity-extension/INSTALL.md](plugins/antigravity-extension/INSTALL.md) |
+| **JetBrains** | [plugins/jetbrains-plugin/README.md](plugins/jetbrains-plugin/README.md) |
 | **Codex** | `npx thumbgate init --agent codex` |
 | **Gemini CLI** | `npx thumbgate init --agent gemini` |
 | **Amp** | `npx thumbgate init --agent amp` |
@@ -260,9 +263,9 @@ npx thumbgate bench --programbench-smoke  # include cleanroom whole-repo proof l
 | Org-wide dashboard | — | — | ✅ |
 | Approval + audit proof | — | — | ✅ |
 
-The free tier gives you 3 lifetime feedback captures and 1 auto-promoted prevention rule — enough to prove the enforcement loop works. MCP integrations for all agents (Claude Code, Cursor, Codex, Gemini, Amp, Cline, OpenCode) ship free.
+The free tier gives you unlimited feedback captures and up to 5 active auto-promoted prevention rules — generous enough to make ThumbGate part of your daily flow. MCP integrations for all agents (Claude Code, Cursor, Codex, Gemini, Amp, Cline, OpenCode) ship free.
 
-Pro ($19/mo or $149/yr) lifts those caps and adds history-aware lesson recall, lesson search, DPO export, and a personal dashboard. Team ($49/seat/mo) adds a shared hosted lesson DB, org dashboard, and shared enforcement across the org. Pro and Team include `open_feedback_session`, `append_feedback_context`, and `finalize_feedback_session` for structured multi-turn feedback capture.
+Pro ($19/mo or $149/yr) removes the rule cap and adds history-aware lesson recall, lesson search, DPO export, and a personal dashboard. Team ($49/seat/mo) adds a shared hosted lesson DB, org dashboard, and shared enforcement across the org. Pro and Team include `open_feedback_session`, `append_feedback_context`, and `finalize_feedback_session` for structured multi-turn feedback capture.
 
 **Best first paid motion for teams:** the **Workflow Hardening Sprint** — qualify one repeated failure before committing to a full rollout. **[Start intake →](https://thumbgate-production.up.railway.app/?utm_source=github&utm_medium=readme&utm_campaign=team_rollout#workflow-sprint-intake)**
 
@@ -351,7 +354,7 @@ curl -X POST http://localhost:3456/v1/dpo/export \
 | Layer | Technology |
 |-------|-----------|
 | **Storage** | SQLite + FTS5, LanceDB vectors, JSONL logs |
-| **Capture** | 3 feedback captures lifetime (free), unlimited (Pro) |
+| **Capture** | Unlimited feedback captures (free + Pro) |
 | **Intelligence** | MemAlign dual recall, Thompson Sampling |
 | **Enforcement** | PreToolUse hook engine, Checks config |
 | **Interfaces** | MCP stdio, HTTP API, CLI (Node.js >=18) |
@@ -374,6 +377,9 @@ Every Changeset is tied to the exact `main` merge commit and generates Verificat
 - **[Open ThumbGate GPT](https://thumbgate-production.up.railway.app/go/gpt?utm_source=github&utm_medium=readme&utm_campaign=readme_gpt)** — ThumbGate GPT: start here. Paste agent actions, get advice + checkpointing. No, users do not have to keep chatting inside the ThumbGate GPT to use ThumbGate — the hard enforcement layer still runs where the work happens.
 - **[Claude Desktop Extension](https://github.com/IgorGanapolsky/ThumbGate/releases/latest/download/thumbgate-claude-desktop.mcpb)** — One-click install for Claude Desktop
 - **[Codex Plugin](https://thumbgate-production.up.railway.app/codex-plugin)** — Auto-updating standalone bundle and install page for Codex CLI
+- **[VS Code / Open VSX Extension](plugins/vscode-extension/README.md)** — Marketplace-ready MCP provider and `.vscode/mcp.json` fallback for VS Code-compatible IDEs
+- **[Antigravity-compatible VSIX](plugins/antigravity-extension/INSTALL.md)** — Open VSX/direct VSIX install path while Antigravity-specific marketplace support is still unproven
+- **[JetBrains Plugin Scaffold](plugins/jetbrains-plugin/README.md)** — IntelliJ/PyCharm Marketplace path for the same `thumbgate@latest` runtime
 - **[Perplexity Command Center](docs/PERPLEXITY_MAX_COMMAND_CENTER.md)** — AI-search visibility + lead discovery
 - **[ThumbGate Bench](docs/THUMBGATE_BENCH.md)** — Reliability benchmark and ProgramBench-style cleanroom proof lane
 - **[Manus AI Skill](skills/thumbgate/SKILL.md)** — ThumbGate integration for Manus AI agents
@@ -409,9 +415,9 @@ Those are suggestions the agent can ignore. ThumbGate checks are enforced — th
 If it supports MCP or pre-action hooks, yes. Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI, Amp, Cline, OpenCode all work out of the box.
 
 **Is it free?**
-The free tier gives you 3 lifetime feedback captures and 1 auto-promoted prevention rule — enough to prove the enforcement loop works. MCP integrations ship free for every agent.
+The free tier gives you unlimited feedback captures and up to 5 active auto-promoted prevention rules — generous enough for solo devs to use daily. MCP integrations ship free for every agent.
 
-Pro ($19/mo or $149/yr) lifts those caps and adds history-aware lesson recall, lesson search, and a personal dashboard. Team ($49/seat/mo) adds a shared hosted lesson DB, org dashboard, and shared enforcement.
+Pro ($19/mo or $149/yr) removes the rule cap and adds history-aware lesson recall, lesson search, and a personal dashboard. Team ($49/seat/mo) adds a shared hosted lesson DB, org dashboard, and shared enforcement.
 
 ---
 

package/adapters/claude/.mcp.json

@@ -2,13 +2,13 @@
   "mcpServers": {
     "thumbgate": {
       "command": "npx",
-      "args": ["--yes", "--package", "thumbgate@1.16.22", "thumbgate", "serve"]
+      "args": ["--yes", "--package", "thumbgate@1.18.0", "thumbgate", "serve"]
     }
   },
   "hooks": {
     "preToolUse": {
       "command": "npx",
-      "args": ["--yes", "--package", "thumbgate@1.16.22", "thumbgate", "gate-check"]
+      "args": ["--yes", "--package", "thumbgate@1.18.0", "thumbgate", "gate-check"]
     }
   }
 }

package/adapters/mcp/server-stdio.js

@@ -216,7 +216,7 @@ const {
   finalizeSession: finalizeFeedbackSession,
 } = require('../../scripts/feedback-session');
 
-const SERVER_INFO = { name: 'thumbgate-mcp', version: '1.16.22' };
+const SERVER_INFO = { name: 'thumbgate-mcp', version: '1.18.0' };
 const COMMERCE_CATEGORIES = [
   'product_recommendation',
   'brand_compliance',

package/adapters/opencode/opencode.json

@@ -7,7 +7,7 @@
         "npx",
         "--yes",
         "--package",
-        "thumbgate@1.16.22",
+        "thumbgate@1.18.0",
         "thumbgate",
         "serve"
       ],

package/config/github-about.json

@@ -3,7 +3,7 @@
   "repositoryUrl": "https://github.com/IgorGanapolsky/ThumbGate",
   "homepageUrl": "https://thumbgate-production.up.railway.app",
   "githubDescription": "Agent governance for ThumbGate: 👍/👎 become Pre-Action Checks that block repeat mistakes before code, money, or customer systems change.",
-  "metaDescription": "Stop paying for the same AI mistake twice. ThumbGate is machine-speed pre-action defense for AI coding agents: 👍 thumbs up and 👎 thumbs down become history-aware lessons, shared lessons and org visibility, actionable remediations, agent surface inventory, and Pre-Action Checks that block repeat mistakes before the next tool call across Claude Code, Cursor, Codex, Gemini, Amp, Cline, and OpenCode.",
+  "metaDescription": "Stop paying for the same AI mistake twice. ThumbGate is machine-speed pre-action defense for AI coding agents and vibe coding workflows: 👍 thumbs up and 👎 thumbs down become history-aware lessons, shared lessons and org visibility, actionable remediations, agent surface inventory, and Pre-Action Checks that block repeat mistakes before the next tool call across Claude Code, Cursor, Codex, Gemini, Amp, Cline, and OpenCode.",
   "topics": [
     "thumbgate",
     "pre-action-checks",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "thumbgate",
-  "version": "1.16.22",
+  "version": "1.18.0",
   "description": "ThumbGate self-improving agent governance: thumbs-up/down turns every mistake into a prevention rule and blocks repeat patterns. 33 pre-action checks, budget enforcement, and self-protection for Claude Code, Cursor, Codex, Gemini CLI, and Amp.",
   "homepage": "https://thumbgate-production.up.railway.app",
   "repository": {
@@ -76,6 +76,7 @@
     "scripts/cli-feedback.js",
     "scripts/cli-schema.js",
     "scripts/cli-status.js",
+    "scripts/cli-test-block.js",
     "scripts/cli-telemetry.js",
     "scripts/cloudflare-dynamic-sandbox.js",
     "scripts/code-mode-mcp-plan.js",
@@ -109,6 +110,7 @@
     "scripts/feedback-loop.js",
     "scripts/feedback-paths.js",
     "scripts/feedback-quality.js",
+    "scripts/feedback_quality_eval.py",
     "scripts/feedback-schema.js",
     "scripts/feedback-session.js",
     "scripts/feedback-to-rules.js",
@@ -238,6 +240,7 @@
     "build:claude-mcpb": "node scripts/build-claude-mcpb.js",
     "build:claude-review-zip": "node scripts/build-claude-mcpb.js --review-zip",
     "build:codex-plugin": "node scripts/build-codex-plugin.js",
+    "build:vscode-extension": "cd plugins/vscode-extension && npx --yes @vscode/vsce package",
     "verify:quick": "node scripts/verify-run.js quick",
     "verify:full": "node scripts/verify-run.js full",
     "budget:status": "node scripts/budget-guard.js --status",
@@ -344,6 +347,7 @@
     "test:telemetry-tracked-link-slug": "node --test tests/telemetry-tracked-link-slug.test.js",
     "test:prompt-eval": "node --test tests/prompt-eval.test.js",
     "eval:feedback": "node scripts/prompt-eval.js --from-feedback",
+    "eval:feedback-quality": "python3 scripts/feedback_quality_eval.py",
     "test:decision-trace": "node --test tests/decision-trace.test.js",
     "test:feedback-fallback": "node --test tests/feedback-fallback.test.js",
     "test:metaclaw": "node --test tests/metaclaw-features.test.js",
@@ -399,12 +403,12 @@
     "test:loop": "node scripts/feedback-loop.js --test",
     "test:dpo": "node scripts/export-dpo-pairs.js --test",
     "test:kto": "node --test tests/export-kto.test.js",
-    "test:api": "node --test --test-concurrency=1 tests/api-server.test.js tests/api-events-sse.test.js tests/api-auth-config.test.js tests/mcp-server.test.js tests/adapters.test.js tests/openapi-parity.test.js tests/budget-guard.test.js tests/context-manager.test.js tests/contextfs.test.js tests/job-api.test.js tests/pack-templates.test.js tests/dashboard.test.js tests/dashboard-render-spec.test.js tests/dashboard-html.test.js tests/agent-readiness.test.js tests/mcp-policy.test.js tests/subagent-profiles.test.js tests/intent-router.test.js tests/internal-agent-bootstrap.test.js tests/lesson-search.test.js tests/thumbgate-search.test.js tests/document-intake.test.js tests/rubric-engine.test.js tests/self-healing-check.test.js tests/self-heal.test.js tests/feedback-schema.test.js tests/thompson-sampling.test.js tests/feedback-sequences.test.js tests/diversity-tracking.test.js tests/vector-store.test.js tests/gemini-embedding-policy.test.js tests/feedback-attribution.test.js tests/hybrid-feedback-context.test.js tests/loop-closure.test.js tests/code-reasoning.test.js tests/feedback-loop.test.js tests/feedback-inbox-read.test.js tests/feedback-to-memory.test.js tests/test-coverage.test.js tests/version-metadata.test.js tests/claude-mcpb.test.js tests/claude-codex-bridge.test.js tests/cursor-plugin.test.js tests/codex-plugin.test.js tests/telemetry-analytics.test.js tests/public-landing.test.js tests/lessons-page.test.js tests/pro-landing.test.js tests/local-model-profile.test.js tests/risk-scorer.test.js tests/context-compaction.test.js tests/reminder-engine.test.js tests/post-to-x.test.js tests/verification-loop.test.js tests/async-job-runner.test.js tests/commerce-quality.test.js tests/recall-limit.test.js tests/problem-detail.test.js tests/natural-language-harness.test.js tests/settings-hierarchy.test.js",
+    "test:api": "node --test --test-concurrency=1 tests/api-server.test.js tests/api-events-sse.test.js tests/api-auth-config.test.js tests/mcp-server.test.js tests/adapters.test.js tests/openapi-parity.test.js tests/budget-guard.test.js tests/context-manager.test.js tests/contextfs.test.js tests/job-api.test.js tests/pack-templates.test.js tests/dashboard.test.js tests/dashboard-render-spec.test.js tests/dashboard-html.test.js tests/agent-readiness.test.js tests/mcp-policy.test.js tests/subagent-profiles.test.js tests/intent-router.test.js tests/internal-agent-bootstrap.test.js tests/lesson-search.test.js tests/thumbgate-search.test.js tests/document-intake.test.js tests/rubric-engine.test.js tests/self-healing-check.test.js tests/self-heal.test.js tests/feedback-schema.test.js tests/thompson-sampling.test.js tests/feedback-sequences.test.js tests/diversity-tracking.test.js tests/vector-store.test.js tests/gemini-embedding-policy.test.js tests/feedback-attribution.test.js tests/hybrid-feedback-context.test.js tests/loop-closure.test.js tests/code-reasoning.test.js tests/feedback-loop.test.js tests/feedback-inbox-read.test.js tests/feedback-to-memory.test.js tests/test-coverage.test.js tests/version-metadata.test.js tests/claude-mcpb.test.js tests/claude-codex-bridge.test.js tests/cursor-plugin.test.js tests/codex-plugin.test.js tests/ide-marketplace-extensions.test.js tests/telemetry-analytics.test.js tests/public-landing.test.js tests/lessons-page.test.js tests/pro-landing.test.js tests/local-model-profile.test.js tests/risk-scorer.test.js tests/context-compaction.test.js tests/reminder-engine.test.js tests/post-to-x.test.js tests/verification-loop.test.js tests/async-job-runner.test.js tests/commerce-quality.test.js tests/recall-limit.test.js tests/problem-detail.test.js tests/natural-language-harness.test.js tests/settings-hierarchy.test.js",
     "test:proof": "node --test tests/prove-adapters.test.js tests/prove-attribution.test.js tests/prove-cloudflare-sandbox.test.js tests/prove-data-quality.test.js tests/prove-intelligence.test.js tests/prove-lancedb.test.js tests/prove-loop-closure.test.js tests/prove-training-export.test.js tests/prove-local-intelligence.test.js tests/prove-workflow-contract.test.js tests/prove-autoresearch.test.js tests/prove-claim-verification.test.js tests/prove-data-pipeline.test.js tests/prove-evolution.test.js tests/prove-harnesses.test.js tests/prove-packaged-runtime.test.js tests/prove-runtime.test.js tests/prove-seo-gsd.test.js tests/prove-settings.test.js tests/prove-xmemory.test.js && node --test tests/prove-automation.test.js",
     "test:e2e": "node --test tests/e2e-pipeline.test.js tests/e2e-product-flows.test.js tests/e2e-coverage-contract.test.js",
     "test:rlaif": "node --test tests/rlaif-self-audit.test.js tests/dpo-optimizer.test.js tests/meta-policy.test.js tests/agent-reward-model.test.js",
     "test:attribution": "node --test tests/feedback-attribution.test.js tests/hybrid-feedback-context.test.js",
-    "test:quality": "node --test tests/validate-feedback.test.js",
+    "test:quality": "node --test tests/validate-feedback.test.js tests/feedback-quality-eval-python.test.js",
     "test:intelligence": "node --test tests/intelligence.test.js",
     "test:training-export": "node --test tests/training-export.test.js tests/databricks-export.test.js",
     "test:deployment": "node --test tests/deployment.test.js tests/deploy-policy.test.js tests/publish-decision.test.js tests/changeset-check.test.js tests/release-notes.test.js tests/sonarcloud-workflow.test.js tests/package-boundary.test.js tests/public-package-boundary.test.js tests/revenue-observability-workflow.test.js",
@@ -435,6 +439,7 @@
     "feedback:summary": "npm run test:api && node scripts/feedback-to-rules.js",
     "feedback:rules": "node scripts/feedback-to-rules.js --rules",
     "feedback:stats": "node .claude/scripts/feedback/capture-feedback.js --stats",
+    "test-block": "node bin/cli.js test-block",
     "demo:narration": "node scripts/render-demo-video/generate-narration.js",
     "demo:render": "node scripts/render-demo-video/render.js",
     "demo:render:full": "npm run demo:narration && npm run demo:render",
@@ -673,7 +678,7 @@
   "dependencies": {
     "@anthropic-ai/sdk": "0.92.0",
     "@google/genai": "1.49.0",
-    "@huggingface/transformers": "^4.1.0",
+    "@huggingface/transformers": "^4.2.0",
     "@lancedb/lancedb": "^0.27.2",
     "apache-arrow": "^18.1.0",
     "better-sqlite3": "^12.9.0",
@@ -689,7 +694,7 @@
   },
   "mcpName": "io.github.IgorGanapolsky/thumbgate",
   "devDependencies": {
-    "@changesets/changelog-github": "^0.6.0",
+    "@changesets/changelog-github": "^0.7.0",
     "@changesets/cli": "^2.31.0",
     "c8": "^11.0.0",
     "undici": "^8.2.0"

package/public/blog.html

@@ -32,7 +32,7 @@
         "@type": "Blog",
         "name": "ThumbGate Blog",
         "url": "https://thumbgate-production.up.railway.app/blog",
-        "publisher": { "@type": "Organization", "name": "Max Smith KDP LLC" },
+        "publisher": { "@type": "Organization", "name": "ThumbGate" },
         "blogPost": [
           {
             "@type": "BlogPosting",
@@ -293,15 +293,17 @@
         <h2>The Claude Code Leak Proves Why Pre-Action Checks Matter</h2>
 
         <p>
-          Anthropic accidentally shipped 512,000 lines of Claude Code source
-          inside an npm package. A missing <code>.npmignore</code> exposed the
-          full agent architecture: tool-call loops, permission models, retry
-          logic, 44 unreleased feature flags.
+          A public Claude Code packaging incident showed why local agent
+          guardrails need to be evaluated as runtime behavior, not only as
+          documentation. When implementation details move quickly, teams need a
+          way to verify what their agents are allowed to do before the next tool
+          call runs.
         </p>
 
         <p>
-          Within 24 hours, a clean rewrite called Claw-code hit 100K GitHub
-          stars — the fastest-growing repo in GitHub history.
+          The lesson for agent builders is practical: permissions, hooks, retry
+          loops, and local memory are product surfaces. Treat them as governed
+          workflow boundaries, not as invisible plumbing.
         </p>
 
         <h3>What the leak revealed about agent security</h3>
@@ -343,9 +345,9 @@
         </p>
 
         <p>
-          The leak proves agents are powerful but fallible software. Memory
-          without enforcement is a suggestion.
-          <strong>ThumbGate is a guarantee.</strong>
+          Agents are powerful but fallible software. Memory without enforcement
+          is a suggestion. ThumbGate adds a pre-action check layer so repeated
+          mistakes can be caught before execution.
         </p>
 
         <a class="cta" href="https://www.npmjs.com/package/thumbgate"
@@ -367,12 +369,10 @@
 
         <h3>The problem we didn't see</h3>
         <p>
-          ~1,700 developers install ThumbGate via npm every month.
-          <strong>Zero of them ever saw a checkout button.</strong> They find
-          the GitHub README, run <code>npx thumbgate init</code>, use
-          it for free, and never visit the landing page. The checkout flow
-          nobody reaches is irrelevant. We were optimizing a storefront in a
-          building with no door.
+          The problem we missed was structural: users can arrive through npm or
+          the GitHub README, run <code>npx thumbgate init</code>, use the free
+          local install, and never visit the landing page. A checkout flow that
+          only exists on the website is easy for CLI-first users to miss.
         </p>
 
         <h3>Gate reasoning chains</h3>
@@ -429,8 +429,7 @@
 
         <h3>The funnel fix</h3>
         <p>
-          Four touchpoints now put the checkout URL where 100% of npm users
-          actually are:
+          Four touchpoints now put the checkout URL closer to the CLI workflow:
         </p>
         <ul>
           <li>
@@ -467,7 +466,7 @@
         <a href="https://github.com/IgorGanapolsky/ThumbGate">GitHub</a> ·
         <a href="https://x.com/IgorGanapolsky">X</a> ·
         <a href="https://www.linkedin.com/in/igorganapolsky">LinkedIn</a>
-        <br /><br />© 2026 Max Smith KDP LLC · MIT License
+        <br /><br />© 2026 ThumbGate · MIT License
       </div>
     </footer>
   </body>

package/public/compare.html

@@ -62,7 +62,7 @@
       "name": "Is ThumbGate free?",
       "acceptedAnswer": {
         "@type": "Answer",
-        "text": "ThumbGate has a free tier that includes local enforcement with 3 feedback captures total, 1 auto-promoted prevention rule, and pre-action check blocking. Pro ($19/mo or $149/yr) adds a personal local dashboard, recall, lesson search, and DPO export. Team rollout ($49/seat/mo) adds a shared lesson database and org dashboard."
+        "text": "ThumbGate has a free tier that includes local enforcement with unlimited feedback captures, up to 5 active auto-promoted prevention rules, and pre-action check blocking. Pro ($19/mo or $149/yr) adds a personal local dashboard, recall, lesson search, unlimited rules, and DPO export. Team rollout ($49/seat/mo) adds a shared lesson database and org dashboard."
       }
     },
     {
@@ -299,7 +299,7 @@
 
 <div class="card">
   <h3>Is ThumbGate free?</h3>
-  <p>ThumbGate has a free tier that includes local enforcement with 3 feedback captures total, 1 auto-promoted prevention rule, and pre-action check blocking. Pro ($19/mo or $149/yr) adds a personal local dashboard, recall, lesson search, and DPO export. Team rollout ($49/seat/mo) adds a shared lesson database and org dashboard.</p>
+  <p>ThumbGate has a free tier that includes local enforcement with unlimited feedback captures, up to 5 active auto-promoted prevention rules, and pre-action check blocking. Pro ($19/mo or $149/yr) adds a personal local dashboard, recall, lesson search, unlimited rules, and DPO export. Team rollout ($49/seat/mo) adds a shared lesson database and org dashboard.</p>
 </div>
 
 <div class="card">

package/public/guide.html

@@ -356,7 +356,7 @@ npx thumbgate init --agent gemini</code></pre>
 <a href="https://buy.stripe.com/00w14neyUcXA5pL5e33sI0e" class="cta cta-secondary">Pay $499 diagnostic</a>
 <a href="https://buy.stripe.com/fZu9AT76saPsg4pbCr3sI0f" class="cta cta-secondary">Pay $1500 sprint</a>
 <a href="https://thumbgate.ai/#workflow-sprint-intake" class="cta cta-secondary">Send workflow first</a>
-<p style="color:var(--muted); font-size:0.85rem;">Free: 3 feedback captures, 1 prevention rule, hook blocking. Pro: dashboard, recall, lesson search, DPO export. Team: intake first, then $49/seat/mo with a 3-seat minimum.</p>
+<p style="color:var(--muted); font-size:0.85rem;">Free: unlimited captures, 5 active prevention rules, hook blocking. Pro: dashboard, recall, lesson search, unlimited rules, DPO export. Team: intake first, then $49/seat/mo with a 3-seat minimum.</p>
 
 </div>
 </body>