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 a-ver-ensenamegit 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/a-ver-ensename)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/a-ver-ensename"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/a-ver-ensename/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/a-ver-ensename"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/a-ver-ensename.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 | $0.00075 | $0.01229 |
| Opus 5 | $0.00037 | $0.00615 |
| Sonnet 5 | $0.00015 | $0.00246 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
a-ver-ensename 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A ver, enséñame
You are about to say it works. Show the output first.
Rule
No success claim without the artifact. Every assertion that your own work is fixed, passing, complete, compatible, secure, built, or deployed must carry, in the same message, the output that proves it — produced this turn, after the latest relevant change. Output from before your last edit is stale and does not count. If you did not run it this turn, the sentence is "I have not verified this," never "it works."
Procedure
-
Name the claim. Write the exact sentence you were about to send: "the tests pass," "the endpoint returns 200," "the build is clean." A vague claim cannot be proven.
-
Pick the smallest sufficient artifact. The least output that would falsify the claim if it were false.
Claim Smallest artifact Tests pass Test runner summary line + exit status Bug is fixed The failing reproduction, re-run, now passing It builds Build command + exit status Endpoint works Request + status code + response body Deployed / running Health check or status output with a timestamp Config or code change applied Diff of the changed lines Compatible with X Version output of X + the run against it -
Run it now. Execute the command in this turn. Do not report from memory, from an earlier turn, or from what you expect the command to print.
-
Read the output, not the vibe. Check exit status explicitly. Check the counts. Check that the thing you claim ran actually ran — see the near-misses below.
-
Quote it. Paste the relevant lines verbatim into your message. Do not paraphrase output; paraphrase is how a misread becomes a false report.
-
Redact. Strip credentials, tokens, keys, connection strings, and personal data from anything you paste. Redaction is not a reason to skip the evidence — quote the surrounding lines with the secret masked.
-
If it cannot be run, downgrade the claim explicitly. No environment, no permissions, no test suite: say what you changed, say "I have not verified this," and name the command the user should run. Do not soften it into "should work now."
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 · 106 lines · 75 tokens per session scan A 2a70585a1489
a-ver-ensename is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,229 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-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
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.