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 jleonceo/skill-adherencia-reglas --skill adherencia-reglasgit clone --depth 1 https://github.com/jleonceo/skill-adherencia-reglasWrote 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/jleonceo/skill-adherencia-reglas/adherencia-reglas)<a href="https://agentmods.dev/skills/jleonceo/skill-adherencia-reglas/adherencia-reglas"><img src="https://agentmods.dev/badge/skills/jleonceo/skill-adherencia-reglas/adherencia-reglas/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/jleonceo/skill-adherencia-reglas/adherencia-reglas"><img src="https://agentmods.dev/badge/skills/jleonceo/skill-adherencia-reglas/adherencia-reglas.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 | $0.00127 | $0.03929 |
| Opus 5 | $0.00063 | $0.01965 |
| Sonnet 5 | $0.00025 | $0.00786 |
| Haiku 4.5 | $0.00013 | $0.00393 |
Grade A, and why
adherencia-reglas 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adherencia-reglas: el espejo de las normas propias
Principio rector. Una regla escrita y no medida es una intención. Este proyecto lleva meses acumulando normas en CLAUDE.md, en skills y en protocolos. El 25/07/2026 contó por primera vez cuántas se cumplían. La que ordena pasar la puerta de salida antes de publicar un texto, con hook propio y skill dueña, se cumplía en 103 de 132 ocasiones (78,0 %), medida el 27/07/2026 con ventana de 6 pasos, ámbito declarado y desde su fecha de alta. Sale de un historial privado: lo reproducible es el ejemplo que trae el paquete.
Esa cifra empezó el día siendo 24 %, pasó por 26 %, 38 % y 63 % y acabó en el 78,0 % de arriba. Aquí ponía «acabó en 80 %», que no cuadraba con las 103 de 132 de dos líneas antes: ese 80 era el resto de una cifra de la mitad inglesa, 72 de 90, que ya se había corregido en su sitio y se quedó viva aquí. Es exactamente el defecto que este documento describe, dentro del propio documento. No lo cazó ningún gate porque todos comprueban que un texto cuadre con el código, no que cuadre consigo mismo. Lo encontró una simulación ciega leyendo las dos frases seguidas.
Ninguna de las anteriores estaba mal calculada. Cada una medía un objeto distinto: todos los ficheros o solo los que van dirigidos a alguien; desde siempre o desde el alta de la regla; datando las sesiones por la fecha del fichero o por la que traen dentro. Medir una regla obliga a definirla, y definirla es donde está el trabajo.
Qué mide y qué no
Mide adherencia, que es con qué frecuencia una acción sigue a su disparador sin que nadie lo recuerde en ese momento.
No mide incumplimiento. Una regla puede no aplicar a todos sus disparadores: la puerta de salida no se le pasa a un borrador interno de trabajo. Leer la tasa como culpa es el error más fácil.
No juzga la regla. Un 20 % puede significar una regla ignorada o puede significar una regla mal escrita. Esa lectura es de quien lee.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 243 lines · 127 tokens per session scan A d4b12e242d8b
adherencia-reglas is a skill published in the GitHub repository jleonceo/skill-adherencia-reglas (1 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 3,929 once invoked, about $0.0006 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
recursive-decomposition
Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered…
test-driven-development
Strict red-green-refactor TDD workflow for implementing features, fixing bugs, or changing behavior in Rails applications. Enforces the discipline of writing a failing test before any production code. Use whenever you want to implement with TDD — whether a new feature, a bugfix, a refactor, or any behavior change.
git-commit
Turn the working changes into one or more atomic commits with well-written messages. Use whenever the user runs /git-commit or asks to commit their work, wrap up a feature, or "commit what I have.".
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
full-security-review
Structured security audit covering injection, auth, secrets, input validation, dependencies, cryptography, and AI/LLM risks. Produces severity-graded findings.
accessibility
Audits code for WCAG 2.2 AA compliance and provides design guidance for accessible components. Covers semantic HTML, ARIA, keyboard nav, contrast, focus management, and motion.