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/cache-optimize)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/cache-optimize"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/cache-optimize/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/cache-optimize"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/cache-optimize.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 | $0.00011 | $0.00515 |
| Opus 5.5 | $0.00004 | $0.00206 |
| Sonnet 5.5 | $0.00002 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
cache-optimize 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 cache-optimize — 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.
What it actually says
Command: cache-optimize
Analiza el orden actual de contexto y sugiere reordenamiento para optimizar cache hits.
Usage
/cache-optimize {project-name}
Prerequisites
- Project debe existir en
projects/{project} - Archivos: CLAUDE.md, reglas-negocio.md, equipo.md
- Permiso de lectura en project directory
Analysis
-
Context Load Audit
- Identifica archivos en orden de carga actual
- Mide tamaño de cada archivo (tokens aproximados)
- Identifica cuáles pueden cachéarse
-
Cache Eligibility Check
- ✓ Stable: CLAUDE.md, reglas-negocio.md, equipo.md
- ✓ Moderado: Skill CLAUDE.md, task templates
- ✗ Dynamic: User requests, conversation
-
Current Order Analysis
- Tokens antes de optimización
- Cache hit probability actual
- Detect "thrashing"
-
Recommended Reordering
- Ordena por estabilidad (Level 1→4)
- Propone cache_control placement
- Calcula tokens después optimización
-
Token Savings Estimate
- Tokens de input normal
- Tokens cacheados (90% descuento)
- Ahorro estimado en porcentaje
Output Example
═════════════════════════════════════════════
CACHE OPTIMIZATION ANALYSIS: {project-name}
═════════════════════════════════════════════
📊 CURRENT STATE
├─ Level 1 (PM Foundation): 200 tokens
├─ Level 2 (Project): 500 tokens
├─ Level 3 (Skills): 300 tokens
└─ Level 4 (Dynamic): 150 tokens
💾 CACHE IMPACT
├─ Current hit probability: 45%
├─ Cacheable tokens: 1000
└─ Dynamic tokens: 150
✅ RECOMMENDATIONS
├─ Reorder cache_control placement
├─ Level 2+3 hits in sequential ops
└─ Expected improvement: 65%
💰 TOKEN SAVINGS
├─ Before: 1000 tokens/request
├─ After: 300 tokens/request
└─ Savings: 70%
Examples
/cache-optimize sala-reservas
/cache-optimize ecommerce-platform
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 · 87 lines · 11 tokens per session scan A df4327ddd920
cache-optimize is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 515 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to cache-optimize, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
graphify-sync
Graphify sync is the optional structural-discovery import flow for graph-style project exports. It writes through ./agent-knowledge, but keeps imported graph structure in Evidence/ and Outputs/, not in durable memory.
chain-load
Loads the most recent chain link to continue work from a previous session.
handoff
Emit a handoff artifact for this session (optionally specify a slug).
sm-search
Ad-hoc semantic search over the supamem dual-memory collection.
recall
Search this machine's past AI coding sessions (deja-vu).
context
Cost-routing + semantic-recall management. Sync the workspace into the gateway memory server, query it, or inspect the routing decision for a given task.