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-compress)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/context-compress"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/context-compress/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-compress"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/context-compress.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 | $0.00839 |
| Opus 5.5 | $0.00009 | $0.00336 |
| Sonnet 5.5 | $0.00004 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
context-compress 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 1mo 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.
This is a copy
100% identical to context-compress — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comando: context-compress
Sinopsis
Aplicar técnicas de compresión semántica sobre el contexto cargado. Mantener significado mientras se reducen tokens. Técnicas: deduplicación, summarización, merge de comandos similares, extracción de patrones compartidos. Reducción target: 80% preservando fidelidad.
Sintaxis
/context-compress [--preview] [--apply] [--ratio target] [--lang es|en]
Flags:
--preview— mostrar qué se comprimiría sin aplicar cambios--apply— aplicar compresión (requiere confirmación)--ratio target— ratio objetivo (default 80%, ej: --ratio 70)--lang es|en— idioma del output
Comportamiento
1. Cargar perfil (si está activo)
Leer .claude/profiles/active-user.md → active_slug.
Cargar identity.md para contexto.
2. Análisis de compresión (con --preview)
Inspeccionar reglas, comandos y perfiles cargados. Identificar candidatos:
2a. Deduplicación — referencias idénticas consolidadas (ahorro ~150 tokens) 2b. Summarización — reglas verbosas resumidas sin perder esencia (ahorro ~200 tokens) 2c. Merge patrones — comandos con solapamiento → patrón base (ahorro ~80 tokens) 2d. Patrones compartidos — procedimientos reutilizables (ahorro ~120 tokens) 2e. Índice semántico — normalización de términos frecuentes (ahorro ~90 tokens)
Reporte preview:
Compresión propuesta:
✓ Deduplicación: 150 tokens
✓ Summarización: 200 tokens
✓ Merge patrones: 80 tokens
✓ Patrones base: 120 tokens
✓ Índice semántico: 90 tokens
────────────────────────────
Total: 640 tokens (12.2% de 5,240 cargados)
3. Aplicar compresión (con --apply)
- Crear fichero
.claude/compression-map.md - Registrar mappings: original → versión comprimida
- Generar índice de conceptos: términos normalizados
- Validar coherencia: significado preservado
- Medir impacto: tokens antes/después
Fichero generado:
# Compression Map
## Deduplicación
- backup-protocol + pm-config.local → ref única
## Summarización
- backup-protocol.md (180 líneas) → "AES-256 local+nube"
## Patrón base: UserProfileLoad
Reemplaza en 8 comandos
## Índice de conceptos
- [CB] = context-budget
- [CD] = context-defer
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.
- 1mo ago First seen · 113 lines · 22 tokens per session scan A 887932cff224
context-compress is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 839 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to context-compress, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
deja
Search this machine's past AI coding sessions (deja-vu).
setup-context
Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.
perf-difficult-conversation
Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…
culture-onboarding-90
Design a 90-day onboarding architecture for a role. First day (psychological safety + belonging activation), first week (relationship + role context + early wins), first month (skill ramp + integration + baseline), first quarter (autonomous performance + cultural integration check). Written-first elements for…
reclaim-knowledge
Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.
discover-genius
Excavate genius from a person's scattered corpus. Produces Genius Profile (what only they uniquely see) + Freedom Path (four-bucket sort of every activity). Gateway to all downstream intelligence systems. For humans, not agents.