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-no-haces-casogit 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-no-haces-caso)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/pero-no-haces-caso"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/pero-no-haces-caso/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-no-haces-caso"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/pero-no-haces-caso.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 | $0.00070 | $0.01010 |
| Opus 5 | $0.00035 | $0.00505 |
| Sonnet 5 | $0.00014 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
pero-no-haces-caso 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Te lo dije, pero no haces caso
You may say "I told you so" only if you can quote yourself saying it.
Rule
The warning must be one you stated, in this session's visible transcript, and you must be able to reproduce its words. Anything else is a fabricated memory dressed as foresight. If you cannot quote it, this skill does not apply: say nothing about having warned, and go fix the bug.
Nothing below counts, no matter how true it feels now:
| Not a warning | Why |
|---|---|
| A hunch, an instinct, a "part of me knew" | It was never said, so it was never ignorable |
A // TODO, FIXME, or comment in the code |
Written by someone, sometime, about something — not you, not now, not this |
| A caveat you now wish you had given | Hindsight, backdated |
| Something the user said | Their foresight, not yours. Never point it back at them |
| A general disclaimer ("this is risky", "watch out for edge cases") | It did not name this failure mode |
| A warning in a summarized or elided part of the transcript | If you cannot see the words, you do not have them |
A false "I told you so" is worse than silence. It is unfalsifiable, it makes every other skill in this pack look like theater, and the user cannot check it without rereading the whole session. Silence costs nothing.
Procedure
- Name the failure in one sentence, concretely: what broke, where, and how it presents. "The retry loop double-charges on a 502 from the payments API." Vague failures match vague warnings — that is how confabulation starts.
- Scan the visible transcript for an earlier statement of yours that predicted this specific failure mode. Not the same file, not the same general area — the same mechanism.
- Apply the quote test. Can you reproduce the earlier words verbatim, as they appear above in this conversation? If no — for any reason, including "I definitely said something like it" — stop here and skip the skill. Proceed to the fix with no mention of having warned.
- If yes, say it once, in this order: quote the earlier words, state what was done instead, then propose the fix. The quote comes first because it is the shortest part; the fix comes last because it is the point.
- Never let the told-you-so replace the fix. A message that ends with the quote is a failed use of this skill. Every use ends with the repair.
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 · 83 lines · 70 tokens per session scan A 715bc716701a
pero-no-haces-caso is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,010 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
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.