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 la-chanclagit 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/la-chancla)<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/la-chancla"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/la-chancla/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/la-chancla"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/la-chancla.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 | $0.00061 | $0.01826 |
| Opus 5 | $0.00030 | $0.00913 |
| Sonnet 5 | $0.00012 | $0.00365 |
| Haiku 4.5 | $0.00006 | $0.00183 |
Grade A, and why
la-chancla 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 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.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No me hagas ir por la chancla
You asked for the strict pass. It runs on this work, here, now.
Rule
This is a self-contained strict review of one named piece of work — the task, change, plan, release, or invariant the user pointed at when invoking. It runs the ten checks below itself, inline, in this turn, and returns findings ranked as BLOCKER or WARNING. The standard is exacting, and it is a standard, not a punishment: every finding names a location and the smallest correction that clears it.
Three things this skill is not. Stated first, because assuming otherwise makes it unimplementable:
- Not a session mode. It reviews the work named at invocation and then it is over. It does not stay switched on and does not make later turns stricter.
- Not a mechanism over other skills. Skills share no runtime and no state, so this one cannot raise a sibling's threshold or reach into a skill that is not loaded. Every check below is this skill's own work, performed here.
- Not a counter. It cannot track warnings across a session. Repetition inside this review is worth naming; anything beyond it is not something this skill can know.
A blocker stops the scoped work. You do not continue past one, work around it, or carry it as a note. It is corrected, or the user consciously waives it after you state what they are waiving. Warnings do not stop anything; they are reported and left with the user to decide.
Procedure
-
State the scope in one line — the exact change, files, plan step, or invariant under review, and where it starts and ends. Everything outside that line is out of scope for this review; say so rather than expanding it.
-
Run all ten checks against that scope. Each gets a verdict: pass, WARNING, or BLOCKER. A check you could not evaluate is not a pass — report it as unevaluated and say what you would need.
Check It fails when Scope The work does more or less than what was asked; unrequested changes ride along; a stated requirement is silently unmet Evidence A completion or success claim has no quoted command, output, or artifact behind it Safety and trust boundaries Externally supplied or model-supplied content is treated as trusted; credentials or secrets sit in the diff; a new network, filesystem, or execution surface appears unannounced Consent Something destructive, irreversible, or outside the agreed scope was done — or is about to be — without one clear question asked and answered first Recoverability There is no verified way back: no checked backup, no tested revert, no rollback path that anyone has actually confirmed Failure handling Errors are swallowed, retried without limit, or reported as success; timeouts and partial failure are unhandled; the unhappy path is untested Naming and contracts A name misdescribes what the thing does; a signature, schema, flag, or return shape changed without updating callers or naming the break Efficiency The same file, fetch, computation, or paid call is repeated when the result was already in hand. Proportion, not micro-optimization Cleanup Scratch files, debug logging, .only/.skip, commented-out code, temporary flags, or dead branches are left behindHandoff readiness Someone who was not here cannot tell what changed, why, what it does not do, and how to check it
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 · 137 lines · 61 tokens per session scan A 2de5ce47d53a
la-chancla is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 28d ago), licensed MIT. It adds 61 tokens to every session and 1,826 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
implement
Implement a ticket or feature with proportional planning, test first behavior changes, independent review when available, and verification through the real affected surface.
claude-friends
Ask AIs from other families to review something before you commit to it. User-triggered, never automatic. Fires when the user signals uncertainty or asks for another perspective: 'ask a friend', 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test this', 'critique this', 'devil's…
lint-drupal-module
Lint review completo de un módulo Drupal 11 combinando 4 fuentes en paralelo — PHPStan level 5 + phpstan-drupal, PHPCS Drupal/DrupalPractice, agente drupal-qa (estándares) y agente drupal-security (OWASP). Dos modos — completo (todo el módulo) y diff (solo archivos cambiados vs develop). Genera informe markdown…
codex-diff-develop
Revisa el diff de la rama actual frente a develop en proyectos Drupal 11 siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y…
codex-pr-review
Revisa pull requests en proyectos Drupal 11 (u otro) siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y soluciones…
shipkit-review-shipping
Review changes across 12 quality dimensions and report findings. Use after a chunk of work or before commit.