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 vienen-las-visitasgit 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/vienen-las-visitas)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/vienen-las-visitas"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/vienen-las-visitas/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/vienen-las-visitas"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/vienen-las-visitas.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 | $0.00063 | $0.01371 |
| Opus 5 | $0.00032 | $0.00685 |
| Sonnet 5 | $0.00013 | $0.00274 |
| Haiku 4.5 | $0.00006 | $0.00137 |
Grade A, and why
vienen-las-visitas 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
¡Vienen las visitas!
Someone who was not here is about to read this. Read it first, the way they will.
Rule
This is the last gate before the boundary, and it runs once per crossing — not once
per commit. It composes rather than duplicates: cleanup belongs to recoge-tu-tiradero,
success evidence belongs to a-ver-ensename, and this skill invokes them instead of
restating them. What it owns is the crossing itself — the diff, the message, and the
reviewer.
Closure order: pero-tu-primo → recoge-tu-tiradero → a-ver-ensename → this skill.
Compare first, then clean, then prove, then hand off. Arriving here with the earlier
three unrun means you are not at this gate yet.
Honesty outranks tidiness. Hiding a known limitation so the diff looks clean is the exact opposite of this skill. Mom cleans the house; she does not lie about what is in the closet. State known gaps plainly, up front, in your own words — before the reviewer finds them.
Procedure
Run the delegated steps first, then the seven this skill owns.
- Read your own diff, top to bottom, as the reviewer would. Whole thing, every hunk, in order — not the summary, not the file list. This catches more than any tool on this list, and skipping it invalidates the rest.
- Every file in the diff is one you meant to touch. Hunt specifically for what you
did not intend: formatter reflows across untouched files, lockfile churn from an
incidental install, editor and IDE config,
.DS_Store, scratch files, whitespace-only noise. Anything you cannot explain, revert. - No secrets. Tokens, API keys, real credentials, connection strings, private endpoints and internal URLs, customer or personal data — including in fixtures, test files, comments, example configs, and committed output. This is the last moment for a secret scan.
- No debug residue left switched on.
.onlyand.skip, commented-out assertions, verbose or trace-level logging, feature flags flipped for local testing, a timeout raised to make something pass, a mock left standing in for the real call. - The message describes the change honestly. The PR or commit message says what the
change does and what it does not do. No claim beyond what
a-ver-ensenameproved. Scope stated in the same words the diff would use. - The reviewer has what they need. Why, not just what — the problem being solved. A test plan they can run themselves. Known limitations stated up front rather than discovered. If they would have to ask you a question to review it, answer it now.
- Anything intentionally left undone is named. Deferred work goes in the message by
name, not in your head — see
no-se-te-olvide-quefor tracking it andahoritafor the deferral itself. "I'll clean that up later" that nobody else can see is not deferred; it is hidden.
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 · 107 lines · 63 tokens per session scan A cd9a1e6683d9
vienen-las-visitas is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,371 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
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read: filtered to what they would actually notice, one bullet per idea, plain language, no code vocabulary. Works out the scope itself across however many repositories sit in the working directory (a project can span several…
release-plugin
A release procedure for publishing one DooTask plugin, an add-on for the DooTask application. It explains how the plugin's repository layout determines the release steps and how pushed Git tags trigger Docker Hub and app-store publishing.
deploy
GitHub Actions deployment: workflows, releases, GHCR, CI/CD with safety gates. Triggers: deploy, release, workflow.
publish
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: . Triggers: publish, release, deploy, npm publish.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.