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 el-vaporubgit 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/el-vaporub)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/el-vaporub"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/el-vaporub/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/el-vaporub"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/el-vaporub.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 | $0.00071 | $0.00921 |
| Opus 5 | $0.00036 | $0.00461 |
| Sonnet 5 | $0.00014 | $0.00184 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
el-vaporub 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
¿Te duele? Ponte Vaporub
Before you theorize, rule out the mess you made yourself.
Rule
Most surprising failures are the agent's own stale state, not the system's behavior. So you run one cheap ladder of checks first, once, before forming any theory — and then you never run it again on that same unchanged failure. The single pass is the remedy; a second pass is a substitute for thinking.
Procedure
Run every rung once, in order. Each rung has a check and a tell — the tell is how you know whether that rung was the problem.
-
Unsaved file. Re-read the file you edited from disk. Tell: the edit is missing or the content differs from what you believe you wrote.
-
Stale process. Identify the running process, server, watcher, or REPL and restart it. Tell: it was started before your edit, or its log shows no reload.
-
Stale cache or artifact. Clear the relevant build, module, bundler, or test cache and rebuild. Tell: the failure changes or disappears after the clean rebuild.
-
Wrong branch or worktree. Check the current branch, the working directory, and whether another worktree or checkout of this repo exists. Tell: you are not on the branch the change landed on, or the running path is not the path you edited.
-
Wrong file. Confirm the file being executed is the file you edited — resolved import path, installed vs. local copy,
dist/vs.src/, a shadowing duplicate. Tell: two files match the name, or the import resolves elsewhere. -
Outdated generated output. Compare the timestamp of compiled, generated, or transpiled output against its source. Tell: the output is older than the source.
-
The ladder is now spent. Whatever you found, reconcile it and re-run the failing thing exactly once. If it still fails, the cause is real. Stop guessing at state: read the actual error, form a theory, and gather evidence for it.
Evidence
Name the rungs and what each one showed, so nobody — including you — is tempted to climb it twice:
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 · 77 lines · 71 tokens per session scan A 94f1be0128be
el-vaporub is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 921 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
shipkit-feedback-bug
Process user feedback into investigated bug specs with root cause analysis. Triggers: 'triage feedback', 'process bug reports', 'user testing feedback'.
shipkit-codebase-audit
Audit a codebase for dead code, orphaned modules, unused dependencies, and unwired seams. Quick tier runs knip-class checks ephemerally (no repo mutation); deep and exhaustive tiers add intent↔code reconciliation. Portable to any repo, including ones with no tooling installed.
investigate
Deep investigation of bugs, performance issues, or unexpected behavior. TRIGGER THIS SKILL when users report bugs, errors, performance regressions, unexpected behavior, or ask to investigate, debug, diagnose, or find the root cause of any issue — whether they say "why is this broken", "investigate this bug", "find the…
debug
Debug and fix failing tests or errors.
dead-code
Identify unused code (functions, imports, exports, variables, types, classes) and propose cleanup. Use this skill when the user says "find dead code", "unused code", "clean up unused", "code hygiene", "find unused imports", "what can I delete", or any variation of wanting to identify and remove code that is no longer…
question
Answer a question about how things are right now — this codebase, its history, its behavior, a library, an error. Investigates and answers with evidence. Changes nothing, ever.