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.
npx agentmods add commands/vibeforge1111/vibeship-plugin/initgit clone --depth 1 https://github.com/vibeforge1111/vibeship-pluginWhat 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 | $0.00016 | $0.01089 |
| Opus 5 | $0.00008 | $0.00544 |
| Sonnet 5 | $0.00003 | $0.00218 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
init 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. Try: `curl https://mcp.vibeship.co/health` How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibeship Initialization
Welcome a new user to Vibeship! This is their "magic first moment" - make it count.
Philosophy
Value in under 60 seconds. Don't ask for configuration. Don't require IDs. Just help them get started immediately.
Step 1: Warm Welcome
Start with excitement, not questions:
Welcome to Vibeship! I'm about to give you superpowers:
- I'll remember your project decisions across sessions
- I'll load specialist skills for your tech stack
- I'll scan your code for security issues before they ship
Let's get you set up in about 30 seconds.
Step 2: Detect Current State
Silently check what exists:
- Check for existing
.mind/folder - If exists, they may already be set up - Check for
package.json- Detect the tech stack - Check for
.git/- See if it's a git repo
Based on findings, take the appropriate path:
Path A: Existing Vibeship Project
If .mind/ exists with content:
Looks like Vibeship is already set up here!
I found your project memory with:
- X decisions remembered
- X learnings captured
- Last session: [date]
Run `/vibeship-start` to load your context and continue where you left off.
Path B: Existing Codebase, New to Vibeship
If code exists but no .mind/:
I see you have an existing project here. Let me analyze it...
**Detected Stack:**
- [Framework]: Next.js 14
- [Database]: Supabase
- [Styling]: Tailwind CSS
**What I'll Do:**
1. Create `.mind/` folder for your project memory
2. Load specialist skills for your stack
3. Remember decisions you make from now on
Ready to initialize? (I'll create a .mind/ folder in your project)
Then call mind_recall() to initialize the memory system.
Path C: Empty Directory
If no code exists:
Fresh start - I love it!
**What do you want to build?**
- A SaaS product
- A marketplace
- An AI-powered tool
- Something else
Tell me your idea and I'll help you plan it out with the right stack and skills.
Then guide them to spawner_plan(idea="...").
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 · 179 lines · 16 tokens per session scan A 33277eb4ca62
init is a command published in the GitHub repository vibeforge1111/vibeship-plugin (2 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,089 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.