@dedesfr/prompter 0.8.19 → 0.8.20

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # CHANGELOG
 
+## [0.8.20] - 2026-05-08
+
+### 🔄 Changed
+- **cerebro Skill**: Streamlined session handoff workflow
+  - Project creation now happens directly via API instead of redirecting to browser
+  - Added direct memory ID resume: users can now say "resume memory k97abc" and agents load it instantly
+  - Improved confirmation message with clear instructions on how to load memories in any agent
+- **cerebro Reference**: Complete overhaul of MCP configuration documentation
+  - Reorganized per-agent setup with consistent format (transport, config path, restart needed, verify commands)
+  - Added VS Code MCP configuration for Copilot users
+  - Added stdio binary build instructions and available tools reference table
+  - Simplified verification commands for each agent
+
 ## [0.8.19] - 2026-05-07
 
 ### ✨ Added

package/dist/cli/index.js

@@ -16,7 +16,7 @@ const program = new Command();
 program
     .name('prompter')
     .description('Enhance prompts directly in your AI coding workflow')
-    .version('0.8.19');
+    .version('0.8.20');
 program
     .command('init')
     .description('Initialize Prompter in your project')

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@dedesfr/prompter",
-    "version": "0.8.19",
+    "version": "0.8.20",
     "description": "Enhance prompts directly in your AI coding workflow",
     "type": "module",
     "main": "dist/index.js",

package/skills/cerebro/SKILL.md

@@ -151,7 +151,7 @@ Generate one at `http://localhost:3000` → **Settings → Agent Tokens**. One t
 
 2. **Pick a project slug** — use the current working directory's folder name. Confirm only if the cwd looks generic (home dir, `/tmp`).
 
-3. **Resolve the project ID** via `mcp__cerebro__project_list`. If no project matches the slug, **ask the user** — show them the existing projects and let them choose: pick an existing one, or create a new one at `http://localhost:3000` (Projects → New) and tell you when it's ready. Never silently fall back to a different project.
+3. **Resolve the project ID** via `mcp__cerebro__project_list`. If no project matches the slug, show the existing projects and ask the user whether to pick one or create a new one. If they want a new project, call `mcp__cerebro__project_create` with the slug as the name — no need to open the browser. Never silently fall back to a different project.
 
 4. **Call `memory_create`**:
    - `project`: the slug or ID
@@ -160,13 +160,16 @@ Generate one at `http://localhost:3000` → **Settings → Agent Tokens**. One t
    - `tags`: `["session-handoff", "<source-agent-name>"]`
    - `metadata`: `{"cwd": "<current working directory>"}`
 
-5. **Confirm** the memory ID to the user so they can verify in the Cerebro dashboard.
+5. **Confirm** the memory ID to the user. Tell them:
+   - They can verify it in the Cerebro dashboard (the ID is shown on each memory card).
+   - In any agent, they can load it instantly by just providing the ID: `"load memory <id>"` → `memory_get({ memoryId: "<id>" })` — no project needed.
 
 ---
 
 ## Resuming a handoff
 
-1. Determine the project slug (cwd folder name, or ask).
+0. **If the user gives you a memory ID directly** (e.g. "resume memory k97abc123"), call `mcp__cerebro__memory_get({ memoryId: "<id>" })` immediately — skip steps 1–3.
+1. Otherwise, determine the project slug (cwd folder name, or ask).
 2. Resolve to a project ID via `project_list` if needed.
 3. Call `memory_search` with query `"session-handoff"`. Filter results to those with `session-handoff` in their tags, sort by `createdAt` descending, take the newest.
 4. Re-state goal and status in one or two sentences and ask if the user wants to start with the first next-step. Don't dump the whole YAML — they want continuity, not a recap wall.

package/skills/cerebro/references/agents.md

@@ -1,94 +1,213 @@
 # Per-Agent MCP Configuration Reference
 
-The installer at `scripts/install_cerebro_mcp.py` writes the cerebro MCP server entry into each detected agent's config file. This document describes what gets written and where, so the user (or you) can verify or hand-edit.
+## Token
 
-## Common token storage
+Generate a token at your Cerebro instance → **Settings → Agent Tokens**. Enter a name (e.g. "My Computer"), click **Issue token**, and copy it immediately — it won't be shown again.
 
-The installer stores credentials at `~/.cerebro/config.json` (mode 0600):
+Tokens are **user-scoped**: one token grants read+write access to all projects, including ones created later.
 
-```json
-{ "url": "http://localhost:3000", "token": "<bearer token>" }
-```
-
-This file is the single source of truth the installer reads on subsequent runs. Override per-agent with the `--token` / `--url` flags if needed.
+---
 
 ## Per-agent details
 
 ### Claude Code
 
-- **Path**: managed via `claude mcp add` CLI (preferred), falls back to `~/.claude/settings.json`.
-- **Transport**: HTTP (`http://localhost:3000/api/mcp` with bearer auth).
-- **Restart needed?** No — picked up on next session.
+- **Transport**: HTTP (no binary needed)
+- **Config**: `claude mcp add` CLI (preferred), or add to `~/.claude/settings.json`
+- **Restart needed?** No
+
+```bash
+claude mcp add --transport http --scope user cerebro \
+  http://localhost:3000/api/mcp \
+  --header "Authorization: Bearer YOUR_TOKEN"
+```
+
+Verify: `claude mcp list` — expect `cerebro  connected`.
+
+---
 
 ### OpenCode
 
-- **Path**: `~/.config/opencode/opencode.json`, `mcp.cerebro` entry.
-- **Transport**: remote HTTP (`type: "remote"`).
-- **Restart needed?** No — picked up on next `opencode` invocation.
+- **Transport**: remote HTTP (no binary needed)
+- **Config**: `~/.config/opencode/opencode.json` or project-root `opencode.json`
+- **Restart needed?** No
+
+```jsonc
+{
+  "$schema": "https://opencode.ai/config.json",
+  "mcp": {
+    "cerebro": {
+      "type": "remote",
+      "url": "http://localhost:3000/api/mcp",
+      "headers": { "Authorization": "Bearer YOUR_TOKEN" },
+      "enabled": true
+    }
+  }
+}
+```
 
-### Codex (OpenAI Codex CLI)
+Verify: `opencode mcp list`
 
-- **Path**: `~/.codex/config.json`, `mcpServers.cerebro` entry.
-- **Transport**: stdio (Codex doesn't currently support remote MCP).
-- **Requires**: `cerebro-mcp-server/dist/index.js` built. The installer builds it automatically if `~/Programming/learn/ai/cerebro/cerebro-mcp-server/` exists; override with `CEREBRO_MCP_SERVER=/path/to/cerebro-mcp-server`.
+---
 
 ### Cursor
 
-- **Path**: `~/.cursor/mcp.json`, `mcpServers.cerebro` entry.
-- **Transport**: stdio.
-- **Restart needed?** **Yes** — full Cursor restart, not just window reload.
+- **Transport**: stdio (requires built binary)
+- **Config**: `~/.cursor/mcp.json`
+- **Restart needed?** **Yes** — full Cursor restart
+
+```json
+{
+  "mcpServers": {
+    "cerebro": {
+      "command": "node",
+      "args": ["/path/to/cerebro-mcp-server/dist/index.js"],
+      "env": {
+        "CEREBRO_URL": "http://localhost:3000",
+        "CEREBRO_TOKEN": "YOUR_TOKEN"
+      }
+    }
+  }
+}
+```
+
+---
+
+### VS Code (GitHub Copilot / Copilot Chat)
+
+- **Transport**: stdio (requires built binary)
+- **Requires**: VS Code 1.99+ with Copilot extension
+- **Config**: `.vscode/mcp.json` (workspace) or user MCP config via Command Palette → **MCP: Open User Configuration**
+- **Restart needed?** Yes
+
+```json
+{
+  "servers": {
+    "cerebro": {
+      "type": "stdio",
+      "command": "node",
+      "args": ["/path/to/cerebro-mcp-server/dist/index.js"],
+      "env": {
+        "CEREBRO_URL": "http://localhost:3000",
+        "CEREBRO_TOKEN": "YOUR_TOKEN"
+      }
+    }
+  }
+}
+```
+
+---
 
 ### Windsurf
 
-- **Path**: `~/.codeium/windsurf/mcp_config.json`, `mcpServers.cerebro` entry.
-- **Transport**: stdio.
-- **Restart needed?** **Yes** — full Windsurf restart.
+- **Transport**: stdio (requires built binary)
+- **Config**: `~/.codeium/windsurf/mcp_config.json`
+- **Restart needed?** **Yes** — full Windsurf restart
+
+```json
+{
+  "mcpServers": {
+    "cerebro": {
+      "command": "node",
+      "args": ["/path/to/cerebro-mcp-server/dist/index.js"],
+      "env": {
+        "CEREBRO_URL": "http://localhost:3000",
+        "CEREBRO_TOKEN": "YOUR_TOKEN"
+      }
+    }
+  }
+}
+```
+
+---
 
 ### Claude Desktop
 
-- **macOS path**: `~/Library/Application Support/Claude/claude_desktop_config.json`.
-- **Windows path**: `%APPDATA%\Claude\claude_desktop_config.json`.
-- **Linux path**: `~/.config/Claude/claude_desktop_config.json`.
-- **Transport**: stdio.
-- **Restart needed?** **Yes**.
+- **Transport**: stdio (requires built binary)
+- **Config**:
+  - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
+  - Windows: `%APPDATA%\Claude\claude_desktop_config.json`
+- **Restart needed?** **Yes**
 
-## Detection rules
+```json
+{
+  "mcpServers": {
+    "cerebro": {
+      "command": "node",
+      "args": ["/path/to/cerebro-mcp-server/dist/index.js"],
+      "env": {
+        "CEREBRO_URL": "http://localhost:3000",
+        "CEREBRO_TOKEN": "YOUR_TOKEN"
+      }
+    }
+  }
+}
+```
+
+---
+
+### Codex CLI
+
+- **Transport**: stdio (requires built binary)
+- **Config**: `~/.codex/config.json`
+- **Restart needed?** No
+
+```json
+{
+  "mcpServers": {
+    "cerebro": {
+      "command": "node",
+      "args": ["/path/to/cerebro-mcp-server/dist/index.js"],
+      "env": {
+        "CEREBRO_URL": "http://localhost:3000",
+        "CEREBRO_TOKEN": "YOUR_TOKEN"
+      }
+    }
+  }
+}
+```
+
+---
 
-The installer considers an agent "installed" if any of these are true:
+## Building the stdio binary
 
-| Agent | Detection signal |
+Required for all stdio-transport agents (Cursor, VS Code, Windsurf, Claude Desktop, Codex CLI):
+
+```bash
+cd /path/to/cerebro-mcp-server
+npm install && npm run build
+# produces dist/index.js — use its absolute path in configs above
+```
+
+---
+
+## Available tools
+
+| Tool | What it does |
 |---|---|
-| `claude` | `claude` CLI on PATH **or** `~/.claude/` exists |
-| `opencode` | `opencode` CLI on PATH **or** `~/.config/opencode/` exists |
-| `codex` | `codex` CLI on PATH **or** `~/.codex/` exists |
-| `cursor` | `~/.cursor/` exists **or** `/Applications/Cursor.app` |
-| `windsurf` | `~/.codeium/` exists **or** `/Applications/Windsurf.app` |
-| `claude-desktop` | `/Applications/Claude.app` **or** OS-specific config dir exists |
+| `project_list` | List all projects (name, slug, ID) |
+| `project_create` | Create a new project |
+| `memory_create` | Create a memory in a project |
+| `memory_get` | Fetch a memory by ID only — no project needed |
+| `memory_update` | Update an existing memory |
+| `memory_delete` | Delete a memory permanently |
+| `memory_list` | List all memories in a project |
+| `memory_search` | Full-text search across a project's memories |
 
-Force a subset with `--agents claude,opencode,codex`. Force-include an undetected agent the same way.
+---
 
 ## Verifying after install
 
 In Claude Code:
-
 ```bash
 claude mcp list
 ```
-
 Expect `cerebro` with status `connected`.
 
 In OpenCode:
-
 ```bash
 opencode mcp list
+opencode mcp debug cerebro
 ```
 
-In a freshly-started Cursor / Windsurf / Claude Desktop, check the tool list (hammer icon or equivalent) for cerebro tools: `project_list`, `memory_create`, `memory_get`, `memory_list`, `memory_search`, `memory_update`, `memory_delete`.
-
-## Uninstall
-
-```bash
-node ~/.claude/skills/session-handoff/scripts/install_cerebro_mcp.js uninstall
-```
-
-Removes the cerebro entry from every detected agent. Pass `--agents` to limit scope. Does **not** delete `~/.cerebro/config.json` — remove that manually if you want to fully reset.
+In stdio-transport agents (Cursor, VS Code, Windsurf, Claude Desktop), check the tool list (hammer icon) for the 8 tools above after restarting.

package/src/cli/index.ts

@@ -18,7 +18,7 @@ const program = new Command();
 program
   .name('prompter')
   .description('Enhance prompts directly in your AI coding workflow')
-  .version('0.8.19');
+  .version('0.8.20');
 
 program
   .command('init')