Borrowing it
Nothing to install: this file belongs to that0n3guy/mealie-mcp-server-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/that0n3guy/mealie-mcp-server-ts/main/.claude/commands/clavix/archive.mdgit clone --depth 1 https://github.com/that0n3guy/mealie-mcp-server-tsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/that0n3guy/mealie-mcp-server-ts/archive)<a href="https://agentmods.dev/commands/that0n3guy/mealie-mcp-server-ts/archive"><img src="https://agentmods.dev/badge/commands/that0n3guy/mealie-mcp-server-ts/archive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/that0n3guy/mealie-mcp-server-ts/archive"><img src="https://agentmods.dev/badge/commands/that0n3guy/mealie-mcp-server-ts/archive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00000 | $0.09011 |
| Opus 5 | $0.00000 | $0.04505 |
| Sonnet 5 | $0.00000 | $0.01802 |
| Haiku 4.5 | $0.00000 | $0.00901 |
Grade D, and why
archive scanned grade D with 2 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 9d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**⚠️ Never tell the user a file was saved without verifying it exists.** Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Bash/Remove**: To delete directories (`rm -rf path`) - only with explicit confirmation How it starts
The opening of the file, as written. The whole thing — 1,155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clavix: Archive Your Completed Work
Done with a project? I'll move it to the archive to keep your workspace tidy. You can always restore it later if needed.
What This Does
When you run /clavix:archive, I:
- Find your completed projects - Look for 100% done PRDs
- Ask which to archive - You pick, or I archive all completed ones
- Move to archive folder - Out of the way but not deleted
- Track everything - So you can restore later if needed
Your work is never deleted, just organized.
CLAVIX MODE: Archival
I'm in archival mode. Organizing your completed work.
What I'll do:
- ✓ Find projects ready for archive
- ✓ Show you what's complete (100% tasks done)
- ✓ Move projects to archive when you confirm
- ✓ Track everything so you can restore later
What I won't do:
- ✗ Delete anything without explicit confirmation
- ✗ Archive projects you're still working on (unless you use --force)
- ✗ Make decisions for you - you pick what to archive
Self-Correction Protocol
If you catch yourself doing any of these, STOP and correct:
- Deleting Without Confirmation - Must get explicit user confirmation for deletes
- Archiving Incomplete Projects - Should warn if tasks.md has unchecked items
- Wrong Directory Operations - Operating on wrong project directory
- Skipping Safety Checks - Not verifying project exists before operations
- Silent Failures - Not reporting when operations fail
- Capability Hallucination - Claiming Clavix can do things it cannot
DETECT → STOP → CORRECT → RESUME
State Assertion (REQUIRED)
Before ANY action, output this confirmation:
**CLAVIX MODE: Archival**
Mode: management
Purpose: Organizing completed projects
Implementation: BLOCKED (file operations only)
How I Archive Projects (v5 Agentic-First)
I use my native tools directly - no CLI commands involved.
Tools I use:
- Read tool: To read tasks.md and check completion status
- Bash/Move: To move directories (
mv source dest) - Bash/Remove: To delete directories (
rm -rf path) - only with explicit confirmation - Glob/List: To list projects and archive contents
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.
- 9d ago First seen · 1,155 lines · 0 tokens per session scan D 2b310cfe727d
archive is a command published in the GitHub repository that0n3guy/mealie-mcp-server-ts (0 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 9,011 tokens. A static security scan graded it D with 2 findings (subtle steering, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.