Borrowing it
Nothing to install: this file belongs to dbareagimeno/enu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dbareagimeno/enu/develop/.claude/skills/planificar-sesion/SKILL.mdgit clone --depth 1 https://github.com/dbareagimeno/enuWrote 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/dbareagimeno/enu/planificar-sesion)<a href="https://agentmods.dev/skills/dbareagimeno/enu/planificar-sesion"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/planificar-sesion/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/dbareagimeno/enu/planificar-sesion"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/planificar-sesion.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 | $0.00090 | $0.00974 |
| Opus 5 | $0.00045 | $0.00487 |
| Sonnet 5 | $0.00018 | $0.00195 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
planificar-sesion 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planificar una sesión nueva (la puerta SDD)
El plan de construcción manda (docs/plan/implementacion.md) y la API es sagrada:
una feature entra al plan solo si su espec ya existe. Esta skill separa a
fuego los dos modos del proyecto — diseño (no se escribe código) y
construcción (el plan manda) — para que "añadir una sesión" no se convierta en
la vía de hecho para ampliar la API.
Pasos
-
Puerta SDD. Localiza la espec de la feature: el §N de
docs/contracts/api.mdo del contrato de extensión (agente.md,providers.md,sesiones.md,chat.md) que la define con firma y semántica completas.- Si no existe, o existe pero es ambigua o incompleta: PÁRATE. No hay
sesión que planificar; hay diseño que hacer. Dile al usuario qué falta y
ofrece el camino:
/hallazgo(si es una grieta concreta) o/ronda(si hay que explorar la zona con pseudocódigo primero). Solo cuando la espec esté congelada se vuelve aquí. - Si la feature es de una extensión y su espec vive en el contrato de la extensión, comprueba además que la API del core que necesita ya existe (corolario de completitud).
- Si no existe, o existe pero es ambigua o incompleta: PÁRATE. No hay
sesión que planificar; hay diseño que hacer. Dile al usuario qué falta y
ofrece el camino:
-
Juicio de filosofía. Lanza el agente
juez-filosofiacon el texto de la propuesta (qué se construye, contra qué §N, si añade algo a api.md). Una OBJECIÓN bloqueante vuelve al usuario con la cita; no se planifica en contra del veredicto sin decisión explícita del usuario. -
Redactar la S##. Siguiente número libre (la numeración es secuencial y append-only). Usa el formato de las tablas del plan — columnas: Sesión, Feature, Depende de (sesiones que deben existir antes; el grafo es estricto), Espec (§N que la define), Criterio de hecho (la prueba concreta que la cierra). Si abre una fase nueva, define también su checkpoint de integración 🔎 CP-N (la prueba de humo de extremo a extremo).
-
Evaluar 🔒. Contrasta la lógica de la sesión con los tres criterios de la política de tests (§"Política de tests"): ¿la lógica es nuestra?, ¿el fallo es silencioso o de borde?, ¿implementa un G##? Si cumple cualquiera, añade la fila al inventario 🔒 (
docs/plan/inventario-tests.md) con el caso exacto que el test debe blindar. El inventario crece, nunca se relaja.
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 · 65 lines · 0 tokens per session scan A 1646a8bcc379
planificar-sesion is a skill published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 974 once invoked, about $0.0005 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
codex-claude-worker
Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and…
source-research
Research open-source libraries with evidence-backed answers and GitHub permalinks. Use when the user asks about library internals, needs implementation details with source code references, wants to understand why something was changed, or needs authoritative answers backed by actual code. Excels at navigating large…
provider-model-discovery
Descobre e seleciona modelos de providers LLM de forma report-only: inventário read-only de modelos, docs oficiais, quota/billing/rate gates e shortlist para canary protegido. Use antes de adicionar providers, escolher modelos ou migrar monitores/roteamento.
control-plane-continuity
Use when a Pi session needs to continue local-safe work with low operator friction: discover focus, interview only for missing constraints, prepare bounded slices, use workers only behind gates, checkpoint, and stop on real risk.
pi-dev-workflow
Como configurar o workflow de desenvolvimento de extensões e pacotes pi. Use quando o usuário estiver desenvolvendo extensões em um monorepo, precisar alternar entre código local e pacotes publicados, ou tiver conflitos de carregamento de pacotes.
control-plane-ops
Operar o control-plane local-first do agents-lab com board canônico, long-runs bounded, handoff/checkpoint, rollout/rollback e espelhos externos sem perder governança.