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/context-health)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/context-health"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/context-health/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/context-health"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/context-health.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 | $0.00077 | $0.02177 |
| Opus 5 | $0.00039 | $0.01089 |
| Sonnet 5 | $0.00015 | $0.00435 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
context-health 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 7d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:context-health
Objetivo
Mostrar el estado de salud de la ventana de contexto en la sesión actual: porcentaje usado, conteo de tokens, archivos cargados y predicción de cuándo comenzará a degradarse la calidad. Sugiere cuándo compactar, qué delegar a subagentes y qué eliminar. Sistema de semáforo: verde (<50%), amarillo (50-75%), rojo (>75%). Rastrea patrones de uso de contexto entre sesiones.
Uso
/dc:context-health # Dashboard completo
/dc:context-health --rapido # Solo semáforo + número
/dc:context-health --sugerir # Recomendaciones accionables
/dc:context-health --historial # Patrones entre sesiones
/dc:context-health --simular 20000 # Simular con N tokens adicionales
/dc:context-health --exportar # Guardar estado para análisis
Comportamiento
-
Medir estado actual del contexto:
- Tokens usados vs límite del modelo activo
- Tokens por categoría: instrucciones del sistema / archivos cargados / conversación / outputs
- Archivos activos en contexto con su peso en tokens
-
Calcular métricas derivadas:
- % de contexto utilizado
- Proyección de agotamiento: si continúa a la tasa actual, ¿en cuántos turnos se llena?
- Zona de degradación: calidad de respuesta empieza a bajar al superar el 75% en la mayoría de modelos
- Densidad de información útil: ratio de tokens de contexto relevante vs tokens acumulados innecesarios
-
Clasificar semáforo:
- 🟢 Verde: < 50% — sin acción requerida
- 🟡 Amarillo: 50-75% — monitorear, preparar compactación
- 🔴 Rojo: > 75% — compactar o delegar antes del próximo turno complejo
-
Generar recomendaciones según estado:
- Qué archivos eliminar del contexto
- Qué subtareas delegar a subagentes
- Cuándo ejecutar
/compact - Qué información preservar en memoria persistente antes de compactar
-
Para
--historial:- Leer
.dc/context-sessions.jsonl - Identificar patrones: ¿en qué tipo de tareas se llena más rápido?
- ¿Cuál es el volumen promedio de tokens por tipo de sesión?
- Leer
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.
- 7d ago First seen · 227 lines · 77 tokens per session scan A 08d528911134
context-health is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,177 once invoked, about $0.0004 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-todo
Capture idea or task as todo from current conversation context.
thread
Persistent context threads for cross-session work that spans phases. Lighter than pause/resume.
note
Zero-friction idea capture. Append, list, or promote notes to todos.
pause
Save your current session state for later resumption.
resume-work
Resume work from previous session with full context restoration.
resume
Pick up where you left off. Restores context and suggests next action.