codekin 0.3.5 → 0.3.7

package/README.md

@@ -3,8 +3,12 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
 [![npm version](https://img.shields.io/npm/v/codekin.svg)](https://www.npmjs.com/package/codekin)
 
+**[codekin.ai](https://codekin.ai)**
+
 Web UI for Claude Code sessions — multi-session support, WebSocket streaming, file uploads, and slash-command skills.
 
+![Codekin screenshot](docs/screenshot.png)
+
 ## Install
 
 **Prerequisites:**
@@ -43,10 +47,17 @@ codekin uninstall               # Remove Codekin entirely
 ## Features
 
 - **Multi-session terminal** — Open and switch between multiple Claude Code sessions, one per repo
+- **Session archive** — Full retrieval and re-activation of archived sessions
 - **Repo browser** — Auto-discovers local repos and GitHub org repos
 - **Screenshot upload** — Drag-and-drop or paste images; the file path is sent to Claude so it can read them natively
 - **Skill browser** — Browse and invoke `/skills` defined in each repo's `.claude/skills/`
 - **Command palette** — `Ctrl+K` to quickly search repos, skills, and actions
+- **Approval management** — Persistent approval storage with detailed per-permission revoking
+- **Mobile-friendly** — Responsive layout that works on phones and tablets
+- **Markdown browser** — Browse and view `.md` files directly in the UI
+- **AI Workflows** — Scheduled code and repository audits and maintenance, with support for custom workflows defined as Markdown files
+- **GitHub webhooks** — Automated bugfixing on CI failures via webhook integration
+- **LLM-powered chores** — Optional API keys (Groq, OpenAI, Gemini, Anthropic) for background tasks like session auto-naming
 
 ## Upgrade
 
@@ -79,7 +90,6 @@ All configuration lives in `~/.config/codekin/env`. Edit this file to override d
 |---|---|---|
 | `PORT` | `32352` | Server port |
 | `REPOS_ROOT` | `~/repos` | Root directory scanned for local repositories |
-| `GH_ORG` | — | Comma-separated GitHub orgs for repo listing |
 | `GROQ_API_KEY` | — | Optional. Enables session auto-naming via Llama 4 Scout (free tier at [groq.com](https://groq.com)) |
 | `OPENAI_API_KEY` | — | Optional. Fallback for session auto-naming via GPT-4o Mini ([platform.openai.com](https://platform.openai.com)) |
 | `GEMINI_API_KEY` | — | Optional. Fallback for session auto-naming via Gemini 2.5 Flash ([aistudio.google.com](https://aistudio.google.com)) |

package/bin/codekin.mjs

@@ -156,6 +156,8 @@ async function cmdSetup({ regenerate = false } = {}) {
     }
   }
 
+
+
   // Write env file
   const frontendDist = findFrontendDist()
   const envVars = {
@@ -219,8 +221,9 @@ function buildPlist() {
   // Inject PATH and HOME so launchd service can find gh, node, etc.
   if (!envVars.PATH && process.env.PATH) envVars.PATH = process.env.PATH
   if (!envVars.HOME) envVars.HOME = homedir()
+  const escXml = (s) => s.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;')
   const envEntries = Object.entries(envVars)
-    .map(([k, v]) => `\t\t<key>${k}</key>\n\t\t<string>${v}</string>`)
+    .map(([k, v]) => `\t\t<key>${escXml(k)}</key>\n\t\t<string>${escXml(v)}</string>`)
     .join('\n')
 
   return `<?xml version="1.0" encoding="UTF-8"?>