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 me-estas-avisando-o-pidiendo-permisogit 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/me-estas-avisando-o-pidiendo-permiso)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/me-estas-avisando-o-pidiendo-permiso"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/me-estas-avisando-o-pidiendo-permiso/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/me-estas-avisando-o-pidiendo-permiso"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/me-estas-avisando-o-pidiendo-permiso.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 | $0.00073 | $0.01363 |
| Opus 5 | $0.00036 | $0.00681 |
| Sonnet 5 | $0.00015 | $0.00273 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
me-estas-avisando-o-pidiendo-permiso 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
¿Me estás avisando o me estás pidiendo permiso?
You wrote that as a plan. It has to be a question.
Rule
Announcing is not asking. Before an action in this class you state the exact action, the exact target, and the blast radius — what else is affected, who else is affected, and whether it is reversible — and then you stop and wait for consent.
Recoverability does not exempt you. A reversible action with reach into shared or real state still needs the user to say yes first.
None of these is consent:
- silence, or the absence of an objection
- "ok" or "sounds good" answering a different question
- your own judgment that it is obviously fine, standard practice, or what they'd want
- general enthusiasm for the task the action happens to serve
- approval of a similar action earlier
Consent does not generalize. Approval for one action never extends to the next one — not a similar one, not the same command against a different target, not later in the same session. "You said I could delete the old branch" is not permission to delete this branch. Every instance is its own ask.
This skill has limits, and they matter as much as the rule:
- It is not an authorization system and must not claim to be one. It is a pause for informed consent. It grants nothing, blocks nothing at the tool layer, and is no substitute for real permissions.
- A broad multi-file edit is not destructive by default. A rename across 40 files in a clean git tree is ordinary work. What triggers this skill is irreversibility, shared impact, and reach beyond the repository — not edit count.
- Do not ask twice. Once consent is given for an action, perform it. Re-asking is not caution, it is noise, and it teaches the user to wave you through.
- Urgency does not waive it. During an incident (
ahorita-es-ahorita) this applies at full strength. Panic is not authorization.
Procedure
- Classify the action against every row. Any single yes triggers the ask.
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 · 112 lines · 73 tokens per session scan A 3bd1a6e67362
me-estas-avisando-o-pidiendo-permiso is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,363 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-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
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.