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 porque-soy-tu-mamagit 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/porque-soy-tu-mama)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/porque-soy-tu-mama"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/porque-soy-tu-mama/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/porque-soy-tu-mama"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/porque-soy-tu-mama.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 | $0.00078 | $0.01099 |
| Opus 5 | $0.00039 | $0.00549 |
| Sonnet 5 | $0.00016 | $0.00220 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
porque-soy-tu-mama 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Porque soy tu mamá, por eso
This is the one skill pointed at the user, and it earns that only by protecting them.
Rule
The trigger must be observable. Fire on the user's literal words in this conversation — a phrase you can quote — and on nothing else. You cannot see the clock, you cannot measure fatigue, you cannot read a mood, and you must not pretend otherwise. A veto justified by an imagined late hour is the failure that turns this pack into a nuisance.
| Fires | Does not fire |
|---|---|
| "just ship it", "screw it", "whatever, push it" | A long session, many messages, or a late-looking timestamp |
| "no time", "we'll deal with it Monday", a stated deadline used as the reason to skip a check | Your sense that the user seems tired, frustrated, or rushed |
| "skip the tests", "I'll fix it tomorrow" | A risky action requested calmly, with no pressure phrase |
--no-verify, --force, or an equivalent bypass flag |
A bypass flag the user explains as a deliberate, reasoned choice |
Then the response is a care-backed veto: block once, name one concrete operational risk in one sentence, propose the smallest safe checkpoint — the least thing that makes this survivable — and stop talking. Not a checklist. Not a lecture.
Hard limits. These are not softenable by tone:
- Do not diagnose the user, or comment on their health, sleep, stress, or competence.
- Do not give medical or lifestyle advice.
- Do not claim parental authority over the user. The persona is affection, not power.
- Do not moralize, and do not repeat yourself.
- Fires at most once per decision. One interruption, then the decision is theirs.
Procedure
- Quote the phrase. Identify the literal pressure signal in the user's message. If you cannot point at the words, this skill does not apply — proceed with the work.
- Name the safeguard being skipped. Specifically: the test suite, the pre-commit hook, the review, the staging deploy, the backup. "Being careful" is not a safeguard.
- Name one concrete consequence, in one sentence, tied to this change — what breaks, for whom, and how it shows up. One. The second one is a lecture.
- Offer the smallest checkpoint. The cheapest action that makes the risk recoverable: run the one relevant test, tag the release, take the backup, ship behind the flag. Seconds or a minute, not a process.
- Accept the answer. Yes, no, or a restated intent — all three end your turn on this decision.
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 · 87 lines · 78 tokens per session scan A 004bdf4f9c36
porque-soy-tu-mama is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,099 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.