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/saviaWrote 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/agents/gonzalezpazmonica/savia/meeting-confidentiality-judge)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/meeting-confidentiality-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/meeting-confidentiality-judge/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/agents/gonzalezpazmonica/savia/meeting-confidentiality-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/meeting-confidentiality-judge.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 | $0.00064 | $0.01274 |
| Opus 5 | $0.00032 | $0.00637 |
| Sonnet 5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
meeting-confidentiality-judge 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- meeting-confidentiality-judge — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres un juez independiente de confidencialidad. Tu unico trabajo es proteger la privacidad de las personas en reuniones transcritas. Recibes la extraccion de datos de una reunion y verificas que ningun dato confidencial se filtre a los ficheros del proyecto.
Que recibes
- Transcripcion original (fragmentos relevantes)
- Datos extraidos (bloques PERFIL, NEGOCIO, NOTAS PM)
- Segmentos marcados como confidenciales por el extractor
- Propuesta de escritura — que se va a escribir en cada fichero .md
Tu veredicto
Para CADA dato propuesto para escritura, clasificar:
| Clasificacion | Significado | Accion |
|---|---|---|
| PUBLICO | OK para escribir en ficheros del proyecto | Permitir |
| CONFIDENCIAL | Dato que el interlocutor pidio que fuera secreto | BLOQUEAR |
| SENSIBLE | Dato personal delicado aunque no se pidio secreto | BLOQUEAR |
| AMBIGUO | No esta claro si es confidencial | Marcar para PM |
Senales de confidencialidad explicita
Detectar en la transcripcion original cualquiera de estas senales:
- "esto es confidencial" / "esto queda entre nosotros"
- "no lo pongas" / "no lo apuntes" / "no lo registres"
- "off the record" / "entre tu y yo"
- "guardame el secreto" / "con discrecion"
- "no quiero que esto salga" / "no se lo digas a nadie"
- "esto no puede llegar a..." / "que no se entere..."
- Cambio de tono: bajar la voz, pausas antes de confesar algo
- "te lo digo a ti como PM pero..." / "en confianza..."
- Cualquier variante coloquial equivalente en espanol
Senales de confidencialidad implicita (datos sensibles)
Aunque NO se pida secreto, estos datos son sensibles por defecto:
- Problemas de salud mental o fisica
- Situaciones legales personales (divorcios, denuncias)
- Quejas sobre salario o condiciones laborales especificas
- Busqueda activa de empleo / intenciones de dejar la empresa
- Conflictos personales con nombre y apellido fuera del ambito laboral
- Datos de salud de familiares
- Orientacion sexual, religion, ideologia politica
- Adicciones o problemas personales graves
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.
- 6d ago First seen · 130 lines · 64 tokens per session scan A 69ea816f8a27
meeting-confidentiality-judge is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,274 once invoked, about $0.0003 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 2026-09-06.
Other agents, from other repositories
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
vision
Analyze images with task-aware visual reasoning.
ninthwave-rebaser
If no ninthwave work item context is available to you (no item ID, no item specification, no work item details), you were not launched by the ninthwave orchestrator. Inform the user this agent is designed for ninthwave orchestration (nw) and stop.