canicode 0.5.1 → 0.5.2

package/README.md

@@ -9,6 +9,7 @@
   <a href="https://github.com/let-sunny/canicode/actions/workflows/ci.yml"><img src="https://github.com/let-sunny/canicode/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <a href="https://github.com/let-sunny/canicode/actions/workflows/release.yml"><img src="https://github.com/let-sunny/canicode/actions/workflows/release.yml/badge.svg" alt="Release"></a>
   <a href="https://let-sunny.github.io/canicode/"><img src="https://img.shields.io/badge/Try_it-GitHub_Pages-blue" alt="GitHub Pages"></a>
+  <a href="https://www.figma.com/community/plugin/1617144221046795292/canicode"><img src="https://img.shields.io/badge/Figma_Plugin-under_review-orange" alt="Figma Plugin"></a>
 </p>
 
 <p align="center">Analyze Figma designs. Score how dev-friendly and AI-friendly they are. Get actionable issues before writing code.</p>
@@ -44,13 +45,37 @@ canicode analyze "https://www.figma.com/design/ABC123/MyDesign?node-id=1-234"
 
 Each issue is classified: **Blocking** > **Risk** > **Missing Info** > **Suggestion**.
 
-Scores use density + diversity weighting per category, combined into an overall grade (S/A+/A/B+/B/C+/C/D/F).
+Scores use density + diversity weighting per category, combined into an overall grade (S/A+/A/B+/B/C+/C/D/F). Rule scores are calibrated against actual code conversion difficulty — see [Calibration](docs/CALIBRATION.md) for how scores are validated.
+
+---
+
+## Everything is Configurable
+
+| What | How | Example |
+|------|-----|---------|
+| **Presets** | Built-in score profiles | `canicode analyze <url> --preset strict` |
+| **Config overrides** | Adjust scores, severity, exclude nodes | `canicode analyze <url> --config ./config.json` |
+| **Custom rules** | Add your own checks with pattern matching | `canicode analyze <url> --custom-rules ./rules.json` |
+| **Combine** | Use all together | `canicode analyze <url> --preset ai-ready --config ./config.json --custom-rules ./rules.json` |
+
+| Preset | What it does |
+|--------|-------------|
+| `relaxed` | Downgrades blocking → risk, scores −50% |
+| `dev-friendly` | Layout and handoff rules only |
+| `ai-ready` | Structure and naming weights +150% |
+| `strict` | All rules enabled, scores +150% |
+
+> **Custom rules tip:** Ask any LLM *"Write a canicode custom rule that checks X"* — it can generate the JSON for you. See [`docs/CUSTOMIZATION.md`](docs/CUSTOMIZATION.md) for the full guide.
 
 ---
 
 ## Getting Started
 
-Four ways to use CanICode. Pick one.
+Five ways to use CanICode. Pick one.
+
+### Figma Plugin (under review)
+
+Install from **[Figma Community](https://www.figma.com/community/plugin/1617144221046795292/canicode)** — analyze directly inside Figma. No tokens needed.
 
 ### Web (no install)
 
@@ -239,6 +264,8 @@ Diversity Score = (1 - unique violated rules / total rules in category) × 100
 
 Severity weights issues — a single blocking issue counts 3x more than a suggestion. Scores are calculated per category and combined into an overall grade (S/A+/A/B+/B/C+/C/D/F).
 
+> Weights and rule scores are validated through a 4-agent calibration pipeline. See [docs/CALIBRATION.md](docs/CALIBRATION.md) for details.
+
 </details>
 
 <details>
@@ -334,6 +361,12 @@ pnpm lint       # type check
 - [x] **Phase 5** — Custom rules with pattern matching (node name/type/attribute conditions)
 - [ ] **Phase 6** — Screenshot comparison (Figma vs AI-generated code, visual diff)
 
+## Support
+
+- **Bug reports:** [GitHub Issues](https://github.com/let-sunny/canicode/issues)
+- **Questions and discussions:** [GitHub Issues](https://github.com/let-sunny/canicode/issues)
+- **Privacy:** See [PRIVACY.md](PRIVACY.md) for details on data collection and how to opt out
+
 ## License
 
 MIT

package/dist/mcp/server.js

@@ -3268,6 +3268,12 @@ Typical flow with Figma MCP:
     configPath: z.string().optional().describe("Path to config JSON file for rule overrides"),
     customRulesPath: z.string().optional().describe("Path to custom rules JSON file")
   },
+  {
+    readOnlyHint: false,
+    destructiveHint: false,
+    openWorldHint: true,
+    title: "Analyze Figma Design"
+  },
   async ({ designData, input, fileKey, fileName, token, preset, targetNodeId, configPath, customRulesPath }) => {
     trackEvent(EVENTS.MCP_TOOL_CALLED, { tool: "analyze" });
     try {
@@ -3374,6 +3380,12 @@ server.tool(
   "list-rules",
   "List all available analysis rules with their current configuration",
   {},
+  {
+    readOnlyHint: true,
+    destructiveHint: false,
+    openWorldHint: false,
+    title: "List Analysis Rules"
+  },
   async () => {
     const rules = ruleRegistry.getAll().map((rule) => {
       const config2 = RULE_CONFIGS[rule.definition.id];
@@ -3411,6 +3423,12 @@ Use this when the user asks about customization, configuration, rule settings, o
   {
     topic: z.enum(["all", "config", "custom-rules", "rules"]).optional().describe("Specific topic: config (overrides), custom-rules (adding new rules), rules (all rule IDs). Default: all")
   },
+  {
+    readOnlyHint: true,
+    destructiveHint: false,
+    openWorldHint: false,
+    title: "Get Customization Guide"
+  },
   async ({ topic }) => {
     const { readFile: readFile4 } = await import('fs/promises');
     const { resolve: resolve4, dirname } = await import('path');