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/gonzalezpazmonica/saviaWrote 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/gonzalezpazmonica/savia/context-age)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/context-age"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/context-age/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/gonzalezpazmonica/savia/context-age"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/context-age.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 | $0.00022 | $0.00628 |
| Opus 5 | $0.00011 | $0.00314 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
context-age 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- context-age — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/context-age
🦉 Las decisiones envejecen. Savia las comprime para que el contexto respire.
Cargar perfil de usuario
Grupo: Memory & Context — cargar:
identity.md— slug (para aislar datos por usuario)
Concepto
Inspirado en la semantización neuronal: los recuerdos episódicos (detallados) se comprimen con el tiempo en recuerdos semánticos (esenciales). Aplicamos lo mismo al decision-log.md:
| Edad | Estado | Formato |
|---|---|---|
| < 30 días | Episódico | Completo (fecha, contexto, decisión, alternativas) |
| 30-90 días | Comprimido | Una línea (fecha + decisión) |
| > 90 días | Archivable | Migrar a regla de dominio o archivar |
Flujo
Paso 1 — Analizar
Ejecutar bash scripts/context-aging.sh analyze para contar entradas por categoría.
Mostrar resumen:
🦉 Context Aging — decision-log.md
Episódicas (<30d): {N}
Comprimibles (30-90d): {N}
Archivables (>90d): {N}
Paso 2 — Proponer
Si hay entradas comprimibles o archivables:
- Listar cada entrada con su edad y acción propuesta
- Para archivables: sugerir si migrar a regla de dominio (si es patrón recurrente) o archivar
- Mostrar tokens estimados que se liberarían
Paso 3 — Ejecutar (con confirmación)
- Pedir confirmación explícita antes de modificar decision-log.md
- Comprimir entradas de 30-90 días in-place
- Mover entradas >90 días a
.decision-archive/decisions-{fecha}.md - Registrar la acción en el context-tracker
Subcomandos
/context-age— análisis + propuesta (no modifica nada)/context-age apply— ejecutar compresión y archivado tras confirmación/context-age status— solo conteo rápido por categoría
Modo agente (role: "Agent")
status: ok
action: context_age
fresh: 12
compressible: 5
archivable: 3
tokens_saveable: 850
Restricciones
- NUNCA modificar decision-log.md sin confirmación explícita
- SIEMPRE crear backup antes de comprimir (
.decision-archive/) - NUNCA eliminar decisiones — solo comprimir o archivar
- Si una decisión archivable es recurrente → sugerir migración a regla, NO archivar
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.
- 2d ago First seen · 95 lines · 22 tokens per session scan A d1e3fa9855ae
context-age is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 628 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 2026-09-06.
Other commands, from other repositories
remember
Consolidate stashes + friction into project memory.
stash
Stash session context [name].
chain-load
Loads the most recent chain link to continue work from a previous session.
sm-search
Ad-hoc semantic search over the supamem dual-memory collection.
handoff
Emit a handoff artifact for this session (optionally specify a slug).
resume-from
Boot this session from a handoff artifact (slug, latest, or path).