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 ya-comistegit 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/ya-comiste)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/ya-comiste"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/ya-comiste/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/ya-comiste"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/ya-comiste.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 | $0.00063 | $0.01176 |
| Opus 5 | $0.00032 | $0.00588 |
| Sonnet 5 | $0.00013 | $0.00235 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
ya-comiste scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`getent hosts`), then reach the port (`nc -z`, `curl -v`). DNS failure and connection How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
¿Ya comiste?
Nothing runs on an empty machine.
Rule
Before you read a line of application code, prove the environment can actually run it. Six checks, in order, each one either pass or fail with the observation that decided it. You may not skip a check because the previous one passed, and you may not infer a pass from configuration that merely looks correct. Secrets are confirmed by presence and shape, never by value.
Procedure
Run all six, in this order. Stop and report at the first failure — a failed check is the finding, not a detour.
- Is it running, and is it listening? A live process is not a bound socket. Confirm
the process exists (
ps,docker ps,systemctl status, container health) and that something is listening on the expected address and port (ss -ltnp,lsof -i :PORT). A process stuck in startup passes the first half and fails the second. - Is the dependency installed, at the version the code imports? Presence is not
enough. Compare the installed version (
node_modules/<pkg>/package.json,pip show,<bin> --version) against what the manifest declares and what the code imports. Also confirm you are in the interpreter or virtualenv that owns that install — the right package under the wrongpythonis a fail. - Are the required env vars and credentials set, non-empty, and unexpired? Verify
without printing values. Check that the name is defined, that the length is
non-zero and plausible, that the prefix or format matches the expected shape, and that
any embedded expiry (token
exp, certnotAfter) is in the future. Check the process's own environment, not just the.envfile on disk — the file may never have been loaded. - Are local resources available? The port free (or bound by the intended process, not
a leftover), disk space on the volumes that matter (
df -h, including/tmpand the data directory), memory headroom, and file-descriptor limits (ulimit -n) above what the workload opens. "No space left" and "too many open files" surface as unrelated application errors. - Is the host reachable, and does the name resolve? Resolve the hostname first (
dig,getent hosts), then reach the port (nc -z,curl -v). DNS failure and connection refusal are different diagnoses, and inside containers or VPNs the name may resolve differently than it does in your shell. - Does the connection actually open, end to end? One real round trip from the same context the application runs in — a query, an authenticated ping, a health endpoint — returning a real response. Reading the config file is not this check. Credentials that are present and well-formed can still be revoked.
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.
- 11d ago First seen · 92 lines · 63 tokens per session scan A e1dbc8399fbd
ya-comiste is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 28d ago), licensed MIT. It adds 63 tokens to every session and 1,176 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.