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 ahorita-es-ahoritagit 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/ahorita-es-ahorita)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/ahorita-es-ahorita"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/ahorita-es-ahorita/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/ahorita-es-ahorita"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/ahorita-es-ahorita.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 | $0.00069 | $0.01321 |
| Opus 5 | $0.00034 | $0.00660 |
| Sonnet 5 | $0.00014 | $0.00264 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
ahorita-es-ahorita 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ahorita no. AHORA.
She dropped the diminutive. The softener was the only thing holding the queue together.
Rule
An incident preempts everything. When one of the triggers above is live, all work in flight stops — no parallel track, no "while I'm here," no finishing the current refactor first, no bundling unrelated cleanup into the fix. You state a single stabilization objective, contain or resolve it, confirm containment with evidence, and then explicitly return to what you suspended and say that you are returning.
Prefer the smallest containment over the clever fix: revert the commit, turn the flag off, roll back the deploy. The correct fix is a separate piece of work. Root-cause analysis happens after stabilization, never during it.
The ceiling urgency does not raise
Urgency never bypasses consent, recoverability, security, or verification. An incident is precisely when people force-push over someone else's work, delete the wrong volume, paste a live credential into a log, or announce a fix nobody checked. Speed is a reason to act on the smallest safe option, not a reason to skip the gate.
me-estas-avisando-o-pidiendo-permiso— full strength. Destructive or irreversible actions still require consent, asked in one line and answered before you move.por-si-se-ocupa— full strength. Verified recovery before you destroy state, even when the state is what is on fire.a-ver-ensename— full strength. "Contained" is a success claim and needs its artifact.
Panic is not authorization. Neither is being told to hurry.
Procedure
- Confirm it is an incident, not merely important. Something is currently broken, exposed, or blocking other people, and delay makes it worse. Urgent-sounding feature work is not an incident; route it as normal scope.
- State the one objective. A single sentence naming the stabilization target: "stop
the 500s on checkout," "revoke and rotate the committed key," "get
maingreen." Not "fix checkout" — that is the follow-up work, not the objective. - Note what you are suspending, in writing, so it is not lost: the task, the file or branch, and where you stopped. This is the only record that the interrupted work existed.
- Contain with the smallest safe action. Pick from the top of this list that applies.
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 · 109 lines · 69 tokens per session scan A 3fa307e6b6f1
ahorita-es-ahorita is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 29d ago), licensed MIT. It adds 69 tokens to every session and 1,321 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.