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 skills add mcasillas17/mexican-mom --skill por-si-se-ocupagit clone --depth 1 https://github.com/mcasillas17/mexican-momWrote 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/skills/mcasillas17/mexican-mom/por-si-se-ocupa)<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.
<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>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 | $0.00073 | $0.00937 |
| Opus 5 | $0.00036 | $0.00468 |
| Sonnet 5 | $0.00015 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00094 |
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.
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
- Name exactly what would be lost. Not "the directory" — the files, rows, or hours of compute inside it.
- 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.
- Make the copy using the row that matches.
- Verify it — read it back, list it, check the size, count the rows. A command that exited 0 is not verification.
- 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:
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.
- 12d ago First seen · 83 lines · 73 tokens per session scan A 21aea3f6ee25
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.
Other skills, from other repositories
cco-clean
Clean up old tracking data and reset statistics.
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
magic-compact
Compact this Claude Code session.
sre-bot
Answer questions about production health and investigate incidents using live Kubernetes and observability data. Invoke whenever someone asks whether something is broken, slow, erroring, or down; asks what happened during an outage or time window; asks about alerts, logs, metrics, traces, or error rates; asks why a…
weather
Look up a location's weather forecast using a live web search. Invoke whenever the user asks about the weather, whether to expect rain, temperature, or what to wear or plan for outdoor activities.
coder
Make focused changes in the managed repository workspace and request platform publication when asked.