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-load)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/context-load"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/context-load.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01193 |
| Opus 5 | $0.00016 | $0.00596 |
| Sonnet 5 | $0.00007 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
context-load 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 yesterday.
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-load — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carga de Contexto — Inicio de Sesión
Ejecuta al empezar una sesión nueva para tener contexto completo.
1. Cargar perfil de usuario
- Leer
.claude/profiles/active-user.md→ obteneractive_slug - Si hay perfil activo, cargar (grupo Memory del context-map):
profiles/users/{slug}/identity.md
- Usar slug para aislar memorias por usuario
- Si no hay perfil → continuar con comportamiento por defecto
2. Banner de inicio
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🚀 /context-load — Cargando contexto de sesión
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
3. Detección de stack
Leer CLAUDE.local.md → campo AZURE_DEVOPS_ENABLED.
Mostrar: 📦 Stack: {GitHub-only|Azure DevOps}
4. Protocolo de carga (con progreso)
📋 Paso 1/5 — Workspace y rama...
pwd && git branch --show-current
Verificar raíz (~/claude/).
📋 Paso 2/5 — Memoria persistente y sesión anterior...
Memory store (output/.memory-store.jsonl):
- Si existe → ejecutar
bash scripts/memory-store.sh context --limit 10 - Mostrar últimas decisiones, bugs y patrones agrupados por tipo
- Si no existe → buscar
decision-log.mdcomo fallback (formato legacy)
Último session save (output/sessions/ → fichero más reciente):
- Si existe → leer y mostrar: objetivo, pendientes, contexto para esta sesión
- Si no existe →
ℹ️ Sin sesiones anteriores guardadas
📋 Paso 3/6 — Estado de proyectos...
Leer CLAUDE.local.md → tabla de proyectos activos.
Para cada proyecto, comprobar si existe y mostrar 1 línea de estado:
- Último audit:
output/audits/*-{proyecto}.md→ score si existe - Deuda:
projects/{p}/debt-register.md→ items abiertos si existe - Riesgos:
projects/{p}/risk-register.md→ riesgos críticos si existe
📋 Paso 4/6 — ADRs activos...
Para cada proyecto activo, buscar ADRs con status: accepted:
grep -l "status: accepted" projects/*/adrs/*.md 2>/dev/null
- Si existen → leer título y fecha de cada ADR activo, mostrar resumen (máx. 5 ADRs más recientes)
- Si no existen →
ℹ️ Sin ADRs activos - Formato:
🏛️ ADR-001: {título} ({fecha}) — {proyecto}
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.
- yesterday First seen · 146 lines · 33 tokens per session scan A ad8a39aac134
context-load is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,193 once invoked, about $0.0002 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
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).
context
A project-context command that manages a .context directory containing decision notes, session logs, and history. It helps keep a record of why changes were made across Git branches and commits.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits.
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer.
bm
Ask basemind anything about the current codebase — outlines, refs, callers, git history, blame, diffs, docs, memory.