ahorita-es-ahorita

ahorita-es-ahorita is a skill for Claude Code from mcasillas17/mexican-mom. It costs 69 tokens per session (1,321 once invoked), scanned A, original, MIT.

An urgent-work rule for incidents that must take priority over other tasks. An incident can include a production outage, leaked secret, active security issue, or red build blocking the team.

In plain words
What is it for?
Defining a single stabilization objective, choosing the smallest safe containment action, verifying that the problem is contained, and then returning to paused work.
Why use it?
It keeps the response focused on quickly containing the immediate risk before investigating deeper causes or doing unrelated work.

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 Defining a single stabilization objective, choosing the smallest safe containment action, verifying that the problem is contained, and then returning to paused work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mcasillas17/mexican-mom/ahorita-es-ahorita
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 ahorita-es-ahorita
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 ahorita-es-ahorita

README.md
[![agentmods](https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/ahorita-es-ahorita/github.svg)](https://agentmods.dev/skills/mcasillas17/mexican-mom/ahorita-es-ahorita)
Your own site
<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.

agentmods 80×15 button for ahorita-es-ahorita

Your own site · 80×15
<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>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,321 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 $0.00069 $0.01321
Opus 5 $0.00034 $0.00660
Sonnet 5 $0.00014 $0.00264
Haiku 4.5 $0.00007 $0.00132

Measured 12d ago against content hash 3fa307e6b6f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

skills/ahorita-es-ahorita/SKILL.md · 109 lines

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

  1. 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.
  2. State the one objective. A single sentence naming the stabilization target: "stop the 500s on checkout," "revoke and rotate the committed key," "get main green." Not "fix checkout" — that is the follow-up work, not the objective.
  3. 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.
  4. Contain with the smallest safe action. Pick from the top of this list that applies.

Read the full file on GitHub · 109 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 · 109 lines · 69 tokens per session scan A 3fa307e6b6f1

Subscribe to this mod's changes

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.