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 no-se-te-olvide-quegit 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/no-se-te-olvide-que)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/no-se-te-olvide-que"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/no-se-te-olvide-que/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/no-se-te-olvide-que"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/no-se-te-olvide-que.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 | $0.00072 | $0.01255 |
| Opus 5 | $0.00036 | $0.00628 |
| Sonnet 5 | $0.00014 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
no-se-te-olvide-que 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ah, y no se te olvide que
Something new just arrived. It does not get to walk in without being named.
Rule
Anything that shows up after the scope was set is new scope, and new scope gets said out loud before it gets worked on. Name it in one sentence, then classify it as exactly one of three — never two, never none.
| Class | What it means | What you must do |
|---|---|---|
| IN | It belongs to the current work | Say why it belongs, say what it changes about the plan or the estimate, then do it |
| FOLLOW-UP | Real, but separate work | Record it durably — see ahorita for what a real commitment requires — and say you recorded it |
| BLOCKER | It invalidates work already done or in flight | Stop. Say what is now wrong and what has to be revisited before anything else proceeds |
Never silently absorb it. Quietly folding "one small thing" into work in progress is how a two-hour change becomes three days: the estimate you gave is now false, the diff is now larger than what was agreed, and the user does not know the scope moved because nobody told them. The absorbing is the failure, not the extra work.
This applies to scope you discover, not only scope the user hands you. If you find a second bug while fixing the first, if a file you touched turns out to need a migration, if a test reveals an unrelated break — that is late-arriving scope and it gets the same sentence and the same classification. Self-inflicted scope creep counts.
If completion was already claimed, IN means re-verification. Taking new work in after
"done" makes the previous evidence stale — it described a codebase that no longer exists.
Say so explicitly and run a-ver-ensename again. Do not let the old proof cover the new
change.
Procedure
- Notice the arrival. The tells: a requirement stated after you started, a constraint nobody mentioned during planning, an issue you tripped over, or anything following the words "also," "one more thing," or "while you're in there."
- State it as new scope in one sentence. Literally say that it is new — "that is new scope relative to what we agreed" — before you say anything about doing it.
- Classify it IN, FOLLOW-UP, or BLOCKER. If you cannot tell, ask; an unclassified addition defaults to absorbed, which is the one outcome this skill forbids.
- Act on the class.
- IN — say what it changes about the estimate or the plan, then do it.
- FOLLOW-UP — record it where it will be seen, and say where.
- BLOCKER — stop and surface it; do not continue building on invalidated work.
- Re-verify if you had already claimed completion. New evidence for the new state.
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 · 94 lines · 72 tokens per session scan A b6667fe0b9f3
no-se-te-olvide-que is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,255 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
cco-clean
Clean up old tracking data and reset statistics.
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
magic-compact
Compact this Claude Code session.
sre-bot
Answer questions about production health and investigate incidents using live Kubernetes and observability data. Invoke whenever someone asks whether something is broken, slow, erroring, or down; asks what happened during an outage or time window; asks about alerts, logs, metrics, traces, or error rates; asks why a…
weather
Look up a location's weather forecast using a live web search. Invoke whenever the user asks about the weather, whether to expect rain, temperature, or what to wear or plan for outdoor activities.
coder
Make focused changes in the managed repository workspace and request platform publication when asked.