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/pm-workspaceWrote 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/pm-workspace/adoption-track)<a href="https://agentmods.dev/commands/gonzalezpazmonica/pm-workspace/adoption-track"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/pm-workspace/adoption-track/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/pm-workspace/adoption-track"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/pm-workspace/adoption-track.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 | $0.01176 |
| Opus 5 | $0.00011 | $0.00588 |
| Sonnet 5 | $0.00004 | $0.00235 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
adoption-track 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 8d 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 adoption-track — 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/adoption-track
🦉 Métrica de adopción en tiempo real: ¿quién usa Savia? ¿Qué comanda? ¿Dónde frenan?
Dashboard de adopción por rol, equipo y comando. Detección automática de fricción.
Datos Recopilados
Por cada comando ejecutado:
- Usuario/rol (del perfil activo)
- Timestamp (hora ejecución)
- Comando (ej:
/sprint-status) - Resultado (✅ éxito, ⚠️ con aviso, ❌ error)
- Duración (segundos)
- Contexto (proyecto, sprint actual)
- Proyecto (si aplica)
Almacenado en: output/adoption-tracking.jsonl (append-only log)
Flujo
Paso 1 — Recopilar datos
- Leer logs de ejecución de comandos (últimas N sesiones)
- Extraer: comando, usuario, proyecto, éxito/error, duración
- Agregar con timestamps de sesión
Paso 2 — Calcular métricas por rol
Adoption Rate: % de usuarios del rol que han usado Savia (≥1 comando)
Command Frequency: promedio comandos/usuario/semana
- Baja (<1): usuarios pasivos, no enganchados
- Normal (1-3): usuarios steady
- Alta (>3): power users
Success Rate: % comandos exitosos vs. totales
- <80%: alto dolor, requiere support/training
- 80-95%: normal
-
95%: excelente
Learning Velocity: comando nuevo cada cuántos días (adoptando amplitud)
Paso 3 — Identificar friction points
Frenos por comando (comandos frecuentemente fallidos):
/sprint-statusfalla 30% → prob: config PAT/pbi-createabandono 70% → prob: demasiadas opciones
Frenos por rol:
- QA usa
/qa-dashboardpero no/testplan-generate→ desconoce interconexión - DevOps no toca infra commands → requiere training
Escalones de aprendizaje:
- Salto grande entre L1→L2 → necesita mentoría
Paso 4 — Detectar riesgo de churn
Alertas automáticas:
- Usuario activo hace 2 semanas, sin actividad última semana → ⚠️ churn risk
- Rol con <20% adoption rate → 🔴 critical, necesita intervención
- Command con >50% error rate → 🔴 comando roto o confuso
Paso 5 — Generar recomendaciones
Por rol:
- Tech Lead: "Activo en specs, nunca usa
/debt-track→ sugerir training" - PM: "Alto uso de reportes, pero no planificación → sugerir
/sprint-autoplan" - Developer: "Domina SDD, pero no tests → sugerir
/testplan-generate"
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.
- 8d ago First seen · 136 lines · 22 tokens per session scan A aa38aa296d58
adoption-track is a command published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 1,176 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to adoption-track, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.