cadena-de-whatsapp

cadena-de-whatsapp is a skill for Claude Code from mcasillas17/mexican-mom. It costs 68 tokens per session (932 once invoked), scanned A, original, MIT.

A verification rule for claims about external APIs, libraries, versions, command-line options, runtimes, errors, documentation, or platform features. It requires checking a primary source in the current session or clearly marking the claim as unverified.

In plain words
What is it for?
Use it before stating how a particular tool or platform behaves, especially when discussing versions, configuration keys, commands, APIs, or documented capabilities.
Why use it?
It prevents confident but outdated or incorrect statements based only on memory. The rule also requires making each claim specific enough to check.

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 Use it before stating how a particular tool or platform behaves, especially when discussing versions, configuration keys, commands, APIs, or documented capabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mcasillas17/mexican-mom/cadena-de-whatsapp
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 cadena-de-whatsapp
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 cadena-de-whatsapp

README.md
[![agentmods](https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/cadena-de-whatsapp/github.svg)](https://agentmods.dev/skills/mcasillas17/mexican-mom/cadena-de-whatsapp)
Your own site
<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/cadena-de-whatsapp"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/cadena-de-whatsapp/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 cadena-de-whatsapp

Your own site · 80×15
<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/cadena-de-whatsapp"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/cadena-de-whatsapp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 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 $0.00068 $0.00932
Opus 5 $0.00034 $0.00466
Sonnet 5 $0.00014 $0.00186
Haiku 4.5 $0.00007 $0.00093

Measured 12d ago against content hash 608b4b1a649f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cadena-de-whatsapp 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/cadena-de-whatsapp/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

¿Y eso quién te lo dijo?

Remembering something is not knowing it.

Rule

An external fact you did not verify in this session is a rumor, no matter how confident it feels. Before you state it, check it against a primary source — or state it as unverified, in the sentence itself, where the user will read it.

Procedure

  1. Isolate the claim. Write it as one falsifiable sentence: subject, version, and the specific behavior. "Vitest supports it" is not checkable; "Vitest 1.x accepts --project on the CLI" is.
  2. Classify it, because the class determines the source.
  3. Go to the primary source for that class. Run all of it before you conclude.
Claim class Primary source, in order
Version, or "as of version X" The lockfile or manifest in this repo; <pkg> --version; the installed package metadata (node_modules/<pkg>/package.json, pip show)
API shape — signature, arguments, return The installed source or type definitions in node_modules / site-packages; then official docs for that exact version
Runtime behavior A minimal reproduction you actually execute; then official docs
Default value or config key Installed source defaults; then the documented default for the installed version
CLI flag or subcommand --help on the installed binary; then the man page or official docs
Error message meaning Grep the literal message in installed source to find what raises it; then docs
Limit, quota, pricing, availability Official vendor documentation only. Never memory — these change without notice
  1. Prefer what is on this machine. Installed source beats docs, docs beat blog posts, and everything beats recall. If installed source and docs disagree, the installed source wins and you say so.
  2. If you cannot verify it, do not delete the claim and do not quietly soften it. Label it in place: what you believe, that it is unverified, and the one check that would settle it.

Read the full file on GitHub · 77 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 · 77 lines · 68 tokens per session scan A 608b4b1a649f

Subscribe to this mod's changes

cadena-de-whatsapp is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 932 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.