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/adoption-sandbox)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/adoption-sandbox"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/adoption-sandbox/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/adoption-sandbox"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/adoption-sandbox.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 | $0.00019 | $0.00871 |
| Opus 5 | $0.00010 | $0.00436 |
| Sonnet 5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
adoption-sandbox 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 5d 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:
- adoption-sandbox — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/adoption-sandbox
🦉 "Prueba todo, no pasa nada." Sandbox aislado con datos ficticios.
Experimentar libremente sin riesgo: datos de prueba, sin Azure DevOps real, sin commits.
Objetivo
Que los devs y PMs practiquen comandos de Savia con total seguridad antes de usarlos en producción. Feedback inmediato. Sin estrés.
Estructura del Sandbox
sandbox/
├── projects/
│ └── sandbox-demo/
│ ├── CLAUDE.md ← Config sandbox
│ ├── equipo.md ← Team ficticio
│ ├── reglas-negocio.md ← Domain model ficticio
│ └── data/
│ ├── sprints.json ← Sprint data ficticios
│ ├── work-items.json ← PBIs/Tasks ficticias
│ └── board-state.json ← Board snapshot
├── docs/
│ └── sandbox-guide.md ← Guía de qué experimentar
└── .env.sandbox ← Vars de entorno sandbox
Flujo
Paso 1 — Crear sandbox project
- Crear
projects/sandbox-demo/con estructura estándar - Generar datos de prueba: 2 sprints ficticios, 20 PBIs, 5 personas
- Configura
AZURE_DEVOPS_PROJECTen.env.sandbox→ null/offline - Copiar plantillas de specs, diagramas, para experimentar
Paso 2 — Habilitar comandos en "safe mode"
- Todos los comandos ejecutan pero NO afectan:
- Azure DevOps real (queries simuladas)
- Repos reales (cambios en memoria, no commits)
- Informes reales (generados en
sandbox/output/)
- Mostrar banner: ⚠️ SANDBOX MODE — cambios no persisten
Paso 3 — Invitar a experimentar
- "Intenta
/sprint-statusaquí — sin riesgo" - "Crea un PBI ficticio con
/pbi-create" - "Genera una spec ficticia con
/spec-generate" - "Escribe código en el sandbox sin commits"
- Feedback inmediato: ✅ esto funcionaría, 🔴 aquí te equivocarías
Paso 4 — Rastrear experimentos
- Log:
sandbox/usage-log.jsoncon cada comando ejecutado - Qué intentó: suceso/error
- Duración: ¿rápido o lento?
- Feedback: ¿comprensible? ¿útil?
Paso 5 — Feedback post-sesión
- Resumen: "Ejecutaste 12 comandos, 11 éxito, 1 confusión"
- Áreas de mejora: "La
/pbi-createpodría ser más clara" - Siguiente paso: "¿Listo para usar esto en tu proyecto real?"
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.
- 5d ago First seen · 105 lines · 19 tokens per session scan A 00b31c0fe5b7
adoption-sandbox is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 871 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
wtfp:contribute
Guide a bounded WTF-P contribution from branch creation through a reviewable change request.
project-brief
Convert a technical spec into a PM/CTO-readable executive summary. Simplify technical details, focus on business value.
learn
Learn about Task Master capabilities through interactive exploration.
tickets-implement
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments: every invocation processes the complete current project queue that is ready for implementation.
hive
Query and manage swarm tasks (cells).
status
Check swarm coordination status - workers, messages, reservations.