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.
npx agentmods add commands/doncheli/don-cheli-sdd/driftgit clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote 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/doncheli/don-cheli-sdd/drift)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/drift"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/drift.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 | $0.00081 | $0.01570 |
| Opus 5 | $0.00041 | $0.00785 |
| Sonnet 5 | $0.00016 | $0.00314 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
drift 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:drift
Objetivo
Detectar y reportar divergencias entre las especificaciones Gherkin (.feature) y la cobertura de tests real. Identifica escenarios sin tests, tests sin spec, y comportamientos que difieren entre lo especificado y lo implementado.
Uso
/dc:drift # Analizar todo el proyecto
/dc:drift @specs/features/pagos/ # Analizar dominio específico
/dc:drift --severidad critica # Solo brechas críticas
/dc:drift --formato tabla # Output en tabla (default)
/dc:drift --formato json # Output en JSON (para CI)
Comportamiento
1. DESCUBRIR — Localizar todos los archivos de spec y test
├── Buscar *.feature en specs/features/
├── Buscar *.test.*, *.spec.*, test_*.py en src/ y tests/
└── Leer .dc/config.yaml para rutas personalizadas
2. MAPEAR — Construir mapa spec→test
├── Extraer escenarios de cada archivo .feature
├── Extraer descripciones de cada test
├── Correlacionar por nombre, etiqueta o convención de archivo
└── Detectar duplicados y conflictos
3. ANALIZAR — Clasificar brechas por severidad
├── CRÍTICO: spec existe, cero tests asociados
├── WARNING: test existe, cero spec asociada
└── INFO: cobertura parcial (escenario sin test o test sin escenario)
4. REPORTAR — Generar reporte estructurado con tabla y recomendaciones
Severidades
| Nivel | Condición | Acción recomendada |
|---|---|---|
CRÍTICO |
Escenario Gherkin sin ningún test asociado | Bloquear PR, crear tests |
WARNING |
Test sin escenario Gherkin correspondiente | Crear spec o eliminar test huérfano |
INFO |
Cobertura parcial (happy path sin edge cases, o viceversa) | Completar en próximo sprint |
Output
## Drift Report: mi-proyecto
**Fecha:** 2026-03-28
**Specs analizadas:** 18 archivos .feature (64 escenarios)
**Tests analizados:** 142 tests en 31 archivos
---
### Resumen de Cobertura
| Categoría | Cantidad | % |
|--------------------|----------|---|
| Escenarios cubiertos | 51 | 80% |
| 🔴 Sin tests (CRÍTICO) | 7 | 11% |
| 🟡 Tests sin spec (WARNING) | 6 | 9% |
---
### 🔴 CRÍTICO — Escenarios sin Tests (7)
| Feature | Escenario | Archivo .feature | Tests encontrados |
|---------|-----------|-----------------|-------------------|
| Pagos | Reembolso parcial con cupón activo | specs/features/pagos/reembolso.feature:34 | 0 |
| Auth | Login con MFA por TOTP | specs/features/auth/login.feature:67 | 0 |
| Carrito | Aplicar descuento por volumen (5+ items) | specs/features/carrito/descuentos.feature:12 | 0 |
| ... | ... | ... | ... |
### 🟡 WARNING — Tests sin Spec (6)
| Test | Archivo | Comportamiento descrito | Spec encontrada |
|------|---------|------------------------|-----------------|
| `test_payment_retry_on_timeout` | tests/unit/test_payments.py:89 | Retry en timeout de Stripe | ninguna |
| `test_user_soft_delete` | tests/unit/test_users.py:134 | Soft delete de usuario | ninguna |
| ... | ... | ... | ... |
### ℹ️ INFO — Cobertura Parcial (12)
| Feature | Escenario | Cobertura |
|---------|-----------|-----------|
| Checkout | Pago exitoso | happy path ✅ / error de red ❌ |
| Registro | Email duplicado | happy path ❌ / error ✅ |
| ... | ... | ... |
---
### Recomendaciones
1. **Inmediato:** Crear tests para los 7 escenarios CRÍTICOS antes del próximo release
2. **Próximo sprint:** Documentar en Gherkin los 6 tests huérfanos o eliminarlos
3. **Backlog:** Completar los 12 casos de cobertura parcial
→ Ejecutar `/dc:desglosar` para convertir brechas en tareas
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.
- 2d ago First seen · 162 lines · 81 tokens per session scan A f3731228b9ce
drift is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 25d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,570 once invoked, about $0.0004 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 2026-09-03.
Other commands, from other repositories
verify-work
Validate built features through conversational UAT.
e2e
Create and run E2E tests across web, mobile, and desktop with auto-detection and CLI-first toolchains.
add-phase
Add phase to end of current milestone in roadmap.
remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
research-phase
Research how to implement a phase (standalone — usually use /pbr:plan-phase instead).
reapply-patches
Reapply local modifications after a PBR update.