por-si-se-ocupa

por-si-se-ocupa is a skill for Claude Code from mcasillas17/mexican-mom. It costs 73 tokens per session (937 once invoked), scanned A, original, MIT.

A safety procedure for operations that permanently delete or overwrite data, such as uncommitted files or database records.

In plain words
What is it for?
Use it before deleting files, discarding uncommitted changes, resetting Git, or removing other state that cannot easily be recreated.
Why use it?
It prevents unrecoverable loss by requiring a verified copy before destructive work begins.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mexican-mom plugin — 24 skills shipped together

Good fit Use it before deleting files, discarding uncommitted changes, resetting Git, or removing other state that cannot easily be recreated.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mcasillas17/mexican-mom/por-si-se-ocupa
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.

Any agent
npx skills add mcasillas17/mexican-mom --skill por-si-se-ocupa
Clone the repo
git clone --depth 1 https://github.com/mcasillas17/mexican-mom

Made for: Claude Code.

Or install mexican-mom, the plugin that ships this one along with the rest of its 24 skills.

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 por-si-se-ocupa

README.md
[![agentmods](https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/por-si-se-ocupa/github.svg)](https://agentmods.dev/skills/mcasillas17/mexican-mom/por-si-se-ocupa)
Your own site
<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/por-si-se-ocupa"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/por-si-se-ocupa/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 por-si-se-ocupa

Your own site · 80×15
<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/por-si-se-ocupa"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/por-si-se-ocupa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00073 $0.00937
Opus 5 $0.00036 $0.00468
Sonnet 5 $0.00015 $0.00187
Haiku 4.5 $0.00007 $0.00094

Measured 12d ago against content hash 21aea3f6ee25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

por-si-se-ocupa 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 12d 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.

skills/por-si-se-ocupa/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guárdalo, por si se ocupa

Nothing leaves this house until there is a copy you have actually opened.

Rule

Copy first, then verify the copy exists and is readable, and only then destroy anything. An unverified backup is not a backup. Your report must say where the copy is and how to restore from it — a backup nobody can find is the same as no backup.

This skill does not fire on ordinary edits to clean, committed, git-tracked files. Git is already the copy. Firing on every Write and every Edit is how a safety rule becomes background noise.

Procedure

  1. Name exactly what would be lost. Not "the directory" — the files, rows, or hours of compute inside it.
  2. Ask whether it can be regenerated from source, from git, or from rerunning a cheap command. If yes, proceed without a copy. If no, or if the rerun is expensive, continue.
  3. Make the copy using the row that matches.
  4. Verify it — read it back, list it, check the size, count the rows. A command that exited 0 is not verification.
  5. State the restore path, then destroy.
What would be lost Copy it by
Uncommitted changes to tracked files git stash push -u -m <label>, or a WIP commit on a throwaway branch
Untracked or git-ignored files cp / cp -R to a clearly named path outside the delete target
A stash about to be dropped git stash show -p stash@{0} > <label>.patch, or record the sha from git rev-parse stash@{0}
Database rows or schema A snapshot table (CREATE TABLE t_backup_<date> AS SELECT …) or a dump/export to a file
Bucket, volume, or container contents Sync or copy to another prefix or a local directory first
Expensive build artifact or long-running output Copy the artifact to a named path before the rebuild starts

Migrations and truncations count as destruction. So does overwriting the only copy of generated data.

Evidence

Report the copy and the way back, not the intention to have made one:

Read the full file on GitHub · 83 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. 12d ago First seen · 83 lines · 73 tokens per session scan A 21aea3f6ee25

Subscribe to this mod's changes

por-si-se-ocupa is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 937 once invoked, about $0.0004 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.