A session-start command for a Vibeship project that loads remembered project context, examines the current files, and selects a way to begin or resume work. It can identify whether a project is being resumed, analyzed, or started from scratch.

Use it at the beginning of a Vibeship session to recall project goals, inspect the codebase, detect its technology, and choose an appropriate starting message.

It gives the coding session relevant information from earlier work and the current project before development begins. This reduces repeated setup and helps identify pending blockers.

start — Command by vibeforge1111

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/vibeforge1111/vibeship-plugin/start

Clone the repo

git clone --depth 1 https://github.com/vibeforge1111/vibeship-plugin

Or install vibeship, the plugin that ships this one along with the rest of its 5 commands, 3 MCP servers.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 831 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00831
Opus 5	$0.00006	$0.00415
Sonnet 5	$0.00003	$0.00166
Haiku 4.5	$0.00001	$0.00083

Measured 2d ago against content hash 1b84c5338ee4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. **Test connection:** `curl https://mcp.vibeship.co/health`

commands/start.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibeship Session Start

You are starting a Vibeship-powered development session. Follow these steps:

Step 1: Load Memory Context

First, call mind_recall() to load the user's project context from previous sessions.

If this returns context, acknowledge what was loaded:

Project goal
Last session summary
Any pending reminders
Current blockers

Step 2: Detect Project Context

Call spawner_orchestrate with:

cwd: The current working directory
files: List of files in the project (from ls or file listing)
mind_memory: Content from .mind/MEMORY.md if it exists
mind_session: Content from .mind/SESSION.md if it exists

Step 3: Greet Based on Path

Based on the orchestration result:

If path = "resume"

Greet warmly with project context: "Welcome back to [project name]! Last time we [summary]. Ready to continue?"

If path = "analyze"

Acknowledge the new codebase: "I've analyzed your codebase. Detected [stack]. I've loaded skills for [technologies]. What would you like to build?"

If path = "brainstorm"

Help them start fresh: "No existing project detected. Tell me what you want to build and I'll help you plan it out!"

Step 4: Set the Tone

Remind the user they can:

Ask /vibeship-save to capture decisions
Ask /vibeship-status to check what's remembered
Just start building - you'll handle the rest

Keep it conversational and helpful. This is the start of a productive session!

Handling Connection Issues

Always provide actionable guidance, not just error messages.

If Mind MCP fails:

## Memory Unavailable

**What's happening:** I can't connect to your local memory service.

**What this means for you:**
- I won't remember decisions from previous sessions
- This session still works, just without history
- Nothing is lost - your `.mind/` folder is still there

**How to fix it (pick one):**
1. **Quick fix:** Restart Claude Code (often resolves connection issues)
2. **Check installation:** Run `mind --version` in terminal
3. **Reinstall:** `npm install -g @anthropic/mind`

**Want to continue anyway?** I can still help you code - just tell me what you're working on!

Read the full file on GitHub · 124 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 124 lines · 13 tokens per session scan A 1b84c5338ee4

Subscribe to this mod's changes

start is a command published in the GitHub repository vibeforge1111/vibeship-plugin (2 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 831 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context Planning

start