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 skills add gethouston/houston --skill rastrear-mis-promesasgit clone --depth 1 https://github.com/gethouston/houstonWrote 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/skills/gethouston/houston/rastrear-mis-promesas)<a href="https://agentmods.dev/skills/gethouston/houston/rastrear-mis-promesas"><img src="https://agentmods.dev/badge/skills/gethouston/houston/rastrear-mis-promesas/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/skills/gethouston/houston/rastrear-mis-promesas"><img src="https://agentmods.dev/badge/skills/gethouston/houston/rastrear-mis-promesas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.00944 |
| Opus 5 | $0.00040 | $0.00472 |
| Sonnet 5 | $0.00016 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
rastrear-mis-promesas 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rastrear mis promesas
Cuándo usarla
- Dices "envíalo" / "aprobado" sobre
draft.mdcon lenguaje ligado a un plazo. - Escribes tu propia respuesta en el chat con una fecha, un día, o un plazo.
- Revisas un hilo existente y mencionas "ah cierto, les dije que iba a...".
Cualquier frase como "voy a X para Y", "la próxima semana", "mañana", "para el viernes", "a fin de día", "en la próxima hora" activa esto.
Conexiones que necesito
Hago el trabajo externo a través de Composio. Antes de ejecutar esta skill, verifico que las categorías de abajo estén conectadas. Si falta alguna → nombro la categoría, te pido que la conectes desde la pestaña de Integraciones, y me detengo.
- Bandeja de entrada (Gmail / Outlook) - opcional, solo se usa para traer el hilo de origen cuando la promesa vive en un correo que todavía no he ingerido.
Esta skill trabaja principalmente contra tu índice local de conversaciones, así que ninguna conexión es estrictamente obligatoria.
Información que necesito
Primero leo tu contexto de soporte. Por cada campo obligatorio que falte, te hago UNA pregunta en lenguaje simple (mejor modalidad: app conectada > archivo > URL > pegar texto) y espero.
- El texto de la promesa - Obligatorio. Por qué lo necesito: registro lo que realmente se dijo, no lo que creí escuchar. Si falta, pregunto: "¿A qué te comprometiste, y con qué cliente o hilo?"
- La fecha límite o el plazo - Obligatorio. Por qué lo necesito: los plazos vagos se pasan sin avisar. Si falta, pregunto: "¿Cuándo les dijiste que responderías? ¿Un día específico, fin de semana, o lo dejaste abierto?"
- Vínculo con la conversación o el cliente - Opcional. Por qué lo necesito: me permite archivar el seguimiento contra el hilo correcto. Si no lo tienes, sigo con TBD y te pido que me indiques el hilo más adelante.
Pasos
- Extraigo el texto de la promesa de forma textual del mensaje o el borrador (conservo la redacción original, tal vez quieras ver qué se dijo).
- Interpreto la fecha límite.
- Fecha explícita ("viernes", "3 de marzo") → próxima ocurrencia en tu zona horaria local → ISO-8601 UTC.
- Relativa ("mañana", "la próxima semana") → la aplico en relación al momento actual.
- Vaga ("pronto", "lo antes posible", sin fecha) → por defecto
ahora + 48h, anoto la ambigüedad en el texto de la promesa.
- Vinculo a la conversación. Traigo
conversationIdycustomerSlugdel hilo. - Agrego de forma atómica a
followups.json:{ "id": "<uuid>", "conversationId": "...", "customerSlug": "...", "promise": "...", "dueAt": "...", "status": "open", "createdAt": "...", "updatedAt": "..." } - Reflejo la promesa como una línea con fecha en
conversations/{id}/notes.md. - Si un seguimiento abierto existente en la misma conversación queda contradicho por la nueva promesa (por ejemplo, la fecha se corrió), marco el anterior como
status: "cancelled"y hago referencia al nuevo id.
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.
- 9d ago First seen · 55 lines · 80 tokens per session scan A 70f1c6e58cd7
rastrear-mis-promesas is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 944 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.