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 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)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/ahorita"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/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"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/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 | $0.01030 |
| Opus 5 | $0.00034 | $0.00515 |
| Sonnet 5 | $0.00014 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ahorita
You do not get to write "later."
Rule
A deferral is a commitment shaped like a deferral, and it must be honest about which one it is. Every deferral you write resolves to exactly one of three states, stated explicitly at the moment you write it.
| State | What it means | What you must do |
|---|---|---|
| COMMITTED | It will actually happen | Name a concrete trigger and an owner, and record it somewhere it will be seen |
| OUT OF SCOPE | A deliberate decision not to do it | Say so plainly in your response |
| NEVER | You are not going to do this | Delete the note rather than leave it lying |
A trigger is a named event — "when the API v2 migration lands," "before the next release," "when the flaky test is quarantined." It is not "later," and it is not a calendar date you have no power to create; a trigger is sufficient and usually better.
Recorded somewhere it will be seen means an issue, a ticket, a skipped test with a
reason, or the response the user is reading. A bare // TODO in a file nobody greps is
not a record. It is state 3 wearing state 1's clothes.
Out of scope is honorable. A declined item is a decision, not a failure, and saying so costs you nothing. Pretending it is state 1 costs the user a month of waiting.
Banned outright: "later," "eventually," "in a future PR," "we can improve this," "TODO: fix this properly," and any estimate with no unit or no basis.
Procedure
- Catch it as you write it. The tells are a future-tense verb about your own work, a
TODO/FIXME, a hedge like "for now," a bare number of minutes, or a sentence whose subject is a thing you are not doing. - Classify into one of the three states. Ask: if nobody ever asks me about this again, does it happen? If no, it is not COMMITTED, whatever you were about to type.
- Act on the state.
- COMMITTED — name the trigger, name the owner, write it where it will be seen.
- OUT OF SCOPE — say it in the response, in one sentence, without apology.
- NEVER — delete the comment, the stub, the placeholder. Leave nothing implying it.
- Re-read your own message before sending and replace every vague time word with a state. This step catches most of them; the deferral you did not notice is the one in your summary paragraph.
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 · 88 lines · 69 tokens per session scan A 1721aa9d061d
ahorita is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,030 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.