mealie-mcp-server-ts: Command for Claude Code

.claude/commands/clavix/archive.md

archive is a command for Claude Code from that0n3guy/mealie-mcp-server-ts. It costs 0 tokens per session (9,011 once invoked), scanned D, original, MIT.

A command that moves finished projects into an archive folder instead of deleting them. A PRD is a product requirements document; here, projects are considered finished when all its tasks are complete.

In plain words
What is it for?
Use it to find fully completed projects, choose which ones to archive, move them out of the main workspace, and keep a record for restoration.
Why use it?
It keeps active work easier to find while preserving completed projects for later restoration. It asks for confirmation before moving anything.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is that0n3guy/mealie-mcp-server-ts's own configuration. It tells Claude Code how to work on mealie-mcp-server-ts itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mealie-mcp-server-ts configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/that0n3guy/mealie-mcp-server-ts/main/.claude/commands/clavix/archive.md
Clone the repo
git clone --depth 1 https://github.com/that0n3guy/mealie-mcp-server-ts

Made for: Claude Code.

Wrote 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.

agentmods badge for archive

README.md
[![agentmods](https://agentmods.dev/badge/commands/that0n3guy/mealie-mcp-server-ts/archive/github.svg)](https://agentmods.dev/commands/that0n3guy/mealie-mcp-server-ts/archive)
Your own site
<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.

agentmods 80×15 button for archive

Your own site · 80×15
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,011 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 2b310cfe727d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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
.claude/commands/clavix/archive.md · 1,155 lines

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:

  1. Find your completed projects - Look for 100% done PRDs
  2. Ask which to archive - You pick, or I archive all completed ones
  3. Move to archive folder - Out of the way but not deleted
  4. 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:

  1. Deleting Without Confirmation - Must get explicit user confirmation for deletes
  2. Archiving Incomplete Projects - Should warn if tasks.md has unchecked items
  3. Wrong Directory Operations - Operating on wrong project directory
  4. Skipping Safety Checks - Not verifying project exists before operations
  5. Silent Failures - Not reporting when operations fail
  6. 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

Read the full file on GitHub · 1,155 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.

  1. 9d ago First seen · 1,155 lines · 0 tokens per session scan D 2b310cfe727d

Subscribe to this mod's changes

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.