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/data-policygit 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/data-policy)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/data-policy"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/data-policy.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 | $0.00078 | $0.02060 |
| Opus 5 | $0.00039 | $0.01030 |
| Sonnet 5 | $0.00016 | $0.00412 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
data-policy scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- axios.post / axios.get / axios.put How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:data-policy
Objetivo
Escanear el proyecto para identificar qué datos se procesan, qué fluye hacia proveedores externos (LLMs, APIs, telemetría) y qué se almacena localmente. Genera un documento DATA-POLICY.md con el mapa de flujo de datos y la política de privacidad del proyecto.
Uso
/dc:data-policy # Escanear y generar política completa
/dc:data-policy --solo-escanear # Solo mostrar hallazgos, sin generar doc
/dc:data-policy --formato privacy # Generar PRIVACY.md (orientado a usuarios)
/dc:data-policy --formato data-policy # Generar DATA-POLICY.md (técnico, default)
/dc:data-policy --actualizar # Actualizar doc existente con nuevos hallazgos
Comportamiento
1. ESCANEAR — Analizar código en busca de flujos de datos
├── Llamadas HTTP salientes (fetch, axios, requests, http.client)
├── Configuración de telemetría (Sentry, Datadog, Mixpanel, Segment)
├── Llamadas a LLM APIs (OpenAI, Anthropic, Cohere, etc.)
├── Almacenamiento de datos (DB, archivos, localStorage, cookies)
├── Variables de entorno que sugieren datos sensibles (API_KEY, TOKEN, SECRET)
└── Campos PII en modelos (email, nombre, teléfono, dirección, IP)
2. CLASIFICAR — Categorizar cada flujo por destino y sensibilidad
├── LOCAL: datos que nunca salen del sistema
├── LLM_PROVIDER: código/specs enviados al proveedor de IA
├── THIRD_PARTY: otros servicios externos (pagos, analytics, email)
└── STORAGE: qué se persiste y por cuánto tiempo
3. MAPEAR — Construir diagrama de flujo de datos (texto)
4. GENERAR — Producir documento de política
Categorías de Escaneo
Llamadas HTTP salientes
Patrones detectados:
- fetch("https://...", ...)
- axios.post / axios.get / axios.put
- requests.get / requests.post (Python)
- http.NewRequest (Go)
- RestTemplate / WebClient (Java)
→ Clasificar por dominio destino
Proveedores de LLM
Dominios monitoreados:
- api.openai.com → OpenAI
- api.anthropic.com → Anthropic / Claude
- generativelanguage.googleapis.com → Google Gemini
- api.cohere.ai → Cohere
- api.mistral.ai → Mistral
→ Identificar qué datos se envían en el payload (prompts, código, specs)
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 · 223 lines · 78 tokens per session scan A 54f232ab44a8
data-policy is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 25d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,060 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
add-phase
Add phase to end of current milestone in roadmap.
insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
reapply-patches
Reapply local modifications after a PBR update.
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).
update
Update PBR to latest version with changelog display.