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 pero-tu-primogit 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/pero-tu-primo)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/pero-tu-primo"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/pero-tu-primo/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/pero-tu-primo"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/pero-tu-primo.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 | $0.00060 | $0.01124 |
| Opus 5 | $0.00030 | $0.00562 |
| Sonnet 5 | $0.00012 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
pero-tu-primo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pero tu primo ya se tituló
The cousin only counts if you can open him.
Rule
Before you call your own implementation good, compare it to something specific. The reference must be something you can open in this session and read: another implementation in this repository, a function in the language's standard library, or a dependency already installed on this machine. If you cannot open it, you may not cite it. No remembered comparison, no "lodash does this in three lines," no "the standard approach uses a trie." When there is nothing to open, compare against a measurable property instead — or say there is no gap.
Procedure
- State what your implementation does, in one sentence, at the level of behavior:
the input, the output, and the mechanism. "Dedupes a list by key, preserving first
occurrence, via a
Setover a single pass." - Find an openable reference, in this order. Stop at the first one that actually solves the same problem.
| Reference class | Where to look |
|---|---|
| Another implementation here | Grep for the same operation elsewhere in the repo; read the sibling module, the older version of this file, the test fixtures that predate it |
| Standard library | Read the installed stdlib source or type definitions on this machine (itertools, collections, Array.prototype, slices, std::) |
| Installed dependency | Read the real source in node_modules/<pkg>, site-packages/<pkg>, vendor/, not the README and not memory |
| Nothing openable | Skip to step 5 |
- Open it and read it. Not the docs for it, not its name in a manifest — the code. If reading it shows it solves a different problem, it is not a reference; go back to step 2.
- Name the specific difference. One property, stated concretely: round trips, allocations, queries, branches, time complexity, error paths, lines with the reason the lines differ. "Theirs is shorter" is not a difference; "theirs avoids the intermediate array, so one allocation instead of three" is.
- If no reference was openable, compare against a named measurable property of your own implementation and state the gap plainly — "three queries where one would do" — or state that there is no gap. "No meaningful comparison available" is a valid outcome. Inventing a cousin to fill the silence is the failure this skill exists to stop.
- Decide, and say which: adopt the reference, adapt the idea into your code, or keep yours with the reason it wins here. Then act on it or record the explicit "no change warranted."
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 · 98 lines · 60 tokens per session scan A 8556e4cddfb0
pero-tu-primo is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 29d ago), licensed MIT. It adds 60 tokens to every session and 1,124 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
implement
Implement a ticket or feature with proportional planning, test first behavior changes, independent review when available, and verification through the real affected surface.
claude-friends
Ask AIs from other families to review something before you commit to it. User-triggered, never automatic. Fires when the user signals uncertainty or asks for another perspective: 'ask a friend', 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test this', 'critique this', 'devil's…
lint-drupal-module
Lint review completo de un módulo Drupal 11 combinando 4 fuentes en paralelo — PHPStan level 5 + phpstan-drupal, PHPCS Drupal/DrupalPractice, agente drupal-qa (estándares) y agente drupal-security (OWASP). Dos modos — completo (todo el módulo) y diff (solo archivos cambiados vs develop). Genera informe markdown…
codex-diff-develop
Revisa el diff de la rama actual frente a develop en proyectos Drupal 11 siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y…
codex-pr-review
Revisa pull requests en proyectos Drupal 11 (u otro) siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y soluciones…
shipkit-review-shipping
Review changes across 12 quality dimensions and report findings. Use after a chunk of work or before commit.