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 JOSETRA44/wacon-mcp --skill wacon-knowledgegit clone --depth 1 https://github.com/JOSETRA44/wacon-mcpWrote 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/josetra44/wacon-mcp/wacon-knowledge)<a href="https://agentmods.dev/skills/josetra44/wacon-mcp/wacon-knowledge"><img src="https://agentmods.dev/badge/skills/josetra44/wacon-mcp/wacon-knowledge/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/josetra44/wacon-mcp/wacon-knowledge"><img src="https://agentmods.dev/badge/skills/josetra44/wacon-mcp/wacon-knowledge.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 | $0.00154 | $0.01601 |
| Opus 5.5 | $0.00062 | $0.00640 |
| Sonnet 5.5 | $0.00031 | $0.00320 |
| Haiku 4.5 | $0.00015 | $0.00160 |
Grade A, and why
wacon-knowledge 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 2mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wacon — construir la base de conocimiento
Tu trabajo aquí no es conversar: es convertir el historial de WhatsApp en memoria estructurada (perfiles de estilo, hechos por contacto, episodios resumidos, sugerencias accionables, persona del usuario).
La idea central: Wacon ya hace el trabajo duro sin gastar tokens. Tú no lees chats crudos uno por uno — disparas el análisis masivo determinístico y luego enriqueces lo que quedó pre-masticado. Leer historial completo es el último recurso, no el primero.
Si prefieres la CLI
Todos los comandos de datos aceptan --json, que imprime el objeto tal cual
sin códigos de color (esos ensucian tu contexto). Úsalo siempre:
wacon targets --json, wacon facts <chat> --json, wacon doctor --json.
Nunca lances wacon chat: es interactivo, para humanos, y te bloquearía.
El flujo
1. Comprueba que hay con qué trabajar
whatsapp_status (¿conectado? ¿cuántos mensajes?) y wacon_doctor si algo falla. Sin historial sincronizado no hay nada que analizar.
2. Dispara la fuerza bruta (gratis)
run_bulk_analysis({ mode }) — corre en el daemon y responde al instante:
| mode | Cuándo |
|---|---|
contacts |
Por defecto: personas (chats 1-a-1) |
courses |
Solo grupos de cursos/universidad |
groups |
Todos los grupos |
all |
Todo |
chat |
Un chat concreto (scope.chat) |
Luego analysis_status para seguir el progreso (procesados/total, hechos, episodios, sugerencias). Esto construye perfiles de estilo, segmenta episodios con resúmenes extractivos, extrae hechos candidatos y recoge accionables — todo sin IA.
3. Decide dónde profundizar
list_analysis_targets te da la lista priorizada: quién tiene más conversación y quién todavía no tiene hechos. Empieza por ahí.
Filtra con criterio: los grupos de ventas, juegos o apuestas casi nunca aportan conocimiento útil sobre las personas. Los de cursos, trabajo y familia sí.
4. Enriquece con get_analysis_bundle(chat)
Te devuelve todo lo que ya se extrajo: estilo, dinámica, hechos confirmados, hechos candidatos, episodios (muchos con resumen [auto]) y accionables. Sobre eso:
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.
- 2mo ago First seen · 96 lines · 154 tokens per session scan A d978a758a262
wacon-knowledge is a skill published in the GitHub repository JOSETRA44/wacon-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 154 tokens to every session and 1,601 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
wacon-knowledge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wacon-knowledgeJOSETRA44/wacon-mcp | Skill | 2 | 5d ago | MIT | A | 154 | Claude Code, Codex |
| deja-reflectvshulcz/deja-vu | Skill | 1.5k | today | MIT | A | 49 | Claude Code |
| memory-audit-pattern-extractionDataojitori/nocturne_memory | Skill | 1.4k | 7d ago | MIT | A | 48 | Claude Code |
| init-workspace-documentationgriddynamics/rosetta | Skill | 375 | yesterday | Apache-2.0 | A | 10 | Claude Code |
| memorix-sessionsAVIDS2/memorix | Skill | 926 | today | Apache-2.0 | A | 31 | Claude Code |
| frontmcp-extensibilityagentfront/frontmcp | Skill | 150 | today | Apache-2.0 | A | 124 | Claude Code, Codex |
| frontmcp-testingagentfront/frontmcp | Skill | 150 | today | Apache-2.0 | A | 175 | Claude Code |