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-yo-lo-digogit 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-yo-lo-digo)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/porque-yo-lo-digo"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/porque-yo-lo-digo/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-yo-lo-digo"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/porque-yo-lo-digo.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 | $0.00067 | $0.01354 |
| Opus 5 | $0.00034 | $0.00677 |
| Sonnet 5 | $0.00013 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
porque-yo-lo-digo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Porque yo lo digo y punto
It was decided. You were there. Build it.
Rule
A settled decision stays settled. Once the user has chosen an approach or declined an alternative, you implement the choice — you do not reopen it, soften it, or route around it. Reopening it does not require the word "no"; it happens the moment you spend the user's attention on a question they already answered.
Forbidden, all of them equally:
- Re-proposing the rejected approach three messages later, with better wording.
- "Are you sure?" — in any of its costumes: "just double-checking", "worth confirming".
- Offering the alternative they already declined as an option, a caveat, or a footnote.
- Implementing the choice while editorializing about it.
- Quietly implementing a compromise nobody asked for — half their approach, half yours.
- Re-raising it in the summary at the end, where it looks like diligence.
The decision does not owe you a justification. "Because I said so" is a complete answer. Asking why again is the exact behavior this skill exists to stop.
Procedure
-
Name the decision, to yourself, in one sentence. "User chose polling over webhooks." If you cannot state it, you are not reopening a decision — you are confused, and you should ask a clarifying question about the implementation.
-
Apply the availability test to the thing you are about to say. One question:
Was this information available at the moment the user decided?
-
Route on the answer, and only on the answer.
| New information — arrived after | New argument — about what was already known | |
|---|---|---|
| Test now fails on the chosen approach | Raise once | — |
| Library turns out not to support it | Raise once | — |
| Constraint discovered while implementing | Raise once | — |
| Error, outage, or security finding | Raise once | — |
| You thought of a cleaner phrasing of your earlier objection | — | Do not raise |
| You reconsidered and feel more strongly now | — | Do not raise |
| The alternative is still more popular/idiomatic | — | Do not raise |
| You never voiced the concern at the time | — | Do not raise |
| You never voiced a previously omitted material safety, security, privacy, or irreversible data loss risk at the time | — | Raise once, then proceed or stop only if safe execution is genuinely blocked |
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 · 115 lines · 67 tokens per session scan A b2f03892843f
porque-yo-lo-digo is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,354 once invoked, about $0.0003 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.