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.
git clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote 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/commands/doncheli/don-cheli-sdd/analizar-sesiones)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/analizar-sesiones"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/analizar-sesiones/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/commands/doncheli/don-cheli-sdd/analizar-sesiones"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/analizar-sesiones.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 | $0.00025 | $0.01462 |
| Opus 5 | $0.00013 | $0.00731 |
| Sonnet 5 | $0.00005 | $0.00292 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
analizar-sesiones 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 9d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:analizar-sesiones
Objetivo
Escanear todas las sesiones de Claude en el equipo local, analizar patrones de uso, y generar recomendaciones concretas sobre qué debería convertirse en habilidades reutilizables, plugins, agentes autónomos o instrucciones de proyecto.
Uso
/dc:analizar-sesiones
/dc:analizar-sesiones --periodo <dias>
/dc:analizar-sesiones --formato <resumen|detallado|ejecutivo>
Comportamiento
-
Escanear todas las sesiones de Claude en el equipo
- Ubicación típica:
~/.claude/projects/y sesiones en ficheros JSONL - Incluye: prompts del usuario, respuestas del agente, herramientas usadas, archivos editados
- Ubicación típica:
-
Clasificar cada interacción por tipo:
- Generación de código
- Debugging / corrección de bugs
- Refactoring
- Code review
- Documentación
- Pregunta / Q&A
- Configuración / DevOps
- Diseño / Arquitectura
- Testing
- Scripting / Automatización
-
Analizar patrones de frecuencia:
- ¿Qué tipo de tareas se repiten más?
- ¿Qué archivos se editan con más frecuencia?
- ¿Qué comandos/herramientas se usan más?
- ¿Qué patrones de prompt se repiten?
- ¿Cuántos tokens se consumen por tipo de tarea?
-
Generar recomendaciones en 5 categorías
Output
# Análisis de Sesiones de Claude
## 📊 Resumen de Uso
| Métrica | Valor |
|---------|-------|
| Sesiones analizadas | 47 |
| Período | Últimos 30 días |
| Tokens consumidos | ~2.4M |
| Tipo más frecuente | Generación de código (38%) |
## 🔁 Lo que Hago Más Frecuentemente
| # | Actividad | Frecuencia | Tokens/Sesión |
|---|----------|------------|---------------|
| 1 | Crear componentes React | 23 veces | ~8K |
| 2 | Corregir tests fallidos | 18 veces | ~5K |
| 3 | Escribir endpoints API | 15 veces | ~12K |
| 4 | Refactorizar funciones | 12 veces | ~6K |
| 5 | Generar documentación | 9 veces | ~3K |
## 🧠 Debería Convertirse en HABILIDAD (Skill)
Flujos de trabajo reutilizables que repito constantemente:
| Skill Propuesta | Basada en | Ahorro Estimado |
|----------------|-----------|-----------------|
| `crear-componente-react` | 23 sesiones de creación de componentes | ~40% tokens |
| `fix-test-pattern` | 18 sesiones de debugging de tests | ~30% tokens |
| `api-endpoint-scaffold` | 15 sesiones de creación de APIs | ~50% tokens |
**Formato de skill:**
```yaml
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.
- 9d ago First seen · 159 lines · 25 tokens per session scan A f35ca1e75fcb
analizar-sesiones is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,462 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
add-phase
Add phase to end of current milestone in roadmap.
insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
research-phase
Research how to implement a phase (standalone — usually use /pbr:plan-phase instead).
reapply-patches
Reapply local modifications after a PBR update.
add-todo
Capture idea or task as todo from current conversation context.