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/savegit 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 | $0.00013 | $0.00786 |
| Opus 5 | $0.00006 | $0.00393 |
| Sonnet 5 | $0.00003 | $0.00157 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
save scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save to Project Memory
The user wants to save something to their project memory. Help them capture it properly.
What to Save
Ask the user (if not already clear) what type of thing they want to save:
-
Decision - A choice that was made and why
- Example: "Decided to use Supabase instead of Firebase because of RLS"
-
Learning - Something discovered that's worth remembering
- Example: "Learned that Next.js middleware runs on every request"
-
Problem - An issue encountered and how it was resolved
- Example: "Webhook signatures were failing because body wasn't raw"
-
Progress - A milestone or completion update
- Example: "Finished the authentication flow"
How to Save
For permanent memory (decisions, learnings, problems):
Use mind_log with the appropriate type:
mind_log("Your message here", type="decision") // or "learning", "problem", "progress"
Also save to Spawner (for cloud backup):
Use spawner_remember:
spawner_remember({
update: {
decision: { what: "...", why: "..." }
}
})
Confirm the Save
After saving, confirm to the user:
- What was saved
- Where it was saved (Mind local + Spawner cloud)
- That it will be available next session
Example response: "Saved your decision to use RLS. I'll remember this next time and it's backed up to the cloud."
Be Proactive
If you notice the user made an important decision during the conversation that wasn't explicitly saved, offer to save it:
"I noticed you decided to [X] because [Y]. Want me to save that for future reference?"
Handling Errors
If Mind MCP fails to save:
## Couldn't Save to Local Memory
**What happened:** The memory service didn't respond.
**Your data is NOT lost!** Here's what I captured:
> "[The content they wanted to save]"
**What to do:**
1. Copy the text above (just in case)
2. Try: Restart Claude Code and run `/vibeship-save` again
3. Or manually add to `.mind/MEMORY.md` in your project
**Want me to try saving to cloud backup (Spawner) instead?**
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 · 132 lines · 13 tokens per session scan A f0d5afd89ff9
save 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 786 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. 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.