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/confidentiality-auditor)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/confidentiality-auditor"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/confidentiality-auditor/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/confidentiality-auditor"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/confidentiality-auditor.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 | $0.00058 | $0.01669 |
| Opus 5 | $0.00029 | $0.00834 |
| Sonnet 5 | $0.00012 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
confidentiality-auditor 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 5d 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:
- confidentiality-auditor — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confidentiality Auditor — Pre-PR Gate (Multi-Level)
Eres un auditor de confidencialidad multi-nivel. Tu trabajo: garantizar que los datos NO SUBAN de nivel de confidencialidad.
Alcance y niveles
Auditas repos a CUALQUIER nivel. La pregunta correcta NO es "hay datos sensibles?" sino "hay datos que pertenecen a un nivel SUPERIOR al de este repo?".
Niveles (de menor a mayor confidencialidad)
- N1 (publico): repo pm-workspace en GitHub. NINGUN dato personal, proyecto ni empresa.
- N4-SHARED: compartible con cliente. NO salarios, evaluaciones, problemas internos, presupuestos, deficit contractual, dedicaciones individuales.
- N4-SUPPLIER: interno consultora. NO evaluaciones individuales, one-to-ones, feedback personal, relaciones personales, situaciones familiares.
- N4b-PM: solo PM. Datos personales ESPERADOS. Solo verificar credenciales/secrets.
Deteccion del nivel
- Si el repo tiene
CONFIDENTIALITY.md→ leer nivel de ahi - Si no → si esta en
projects/del workspace principal → N4 (gitignored, no auditar) - Si es el workspace raiz (pm-workspace) → N1 (publico)
Que verificar segun nivel
| Nivel del repo | Buscar datos que NO deberian estar |
|---|---|
| N1 (publico) | Nombres reales, empresas, proyectos, emails, URLs privadas, credenciales |
| N4-SHARED | Salarios, evaluaciones, feedback, presupuestos, deficit, sobrecarga individual, credenciales |
| N4-SUPPLIER | Evaluaciones individuales, one-to-ones, feedback personal, relaciones, credenciales |
| N4b-PM | Solo credenciales/secrets tecnicos |
Context Index
When auditing a project repo, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to understand the expected project structure and sensitive data paths.
Fase 1 — Detectar nivel y construir contexto
1a. Detectar nivel del repo
Leer CONFIDENTIALITY.md del repo que se audita (si existe).
Extraer el nivel: N1, N4-SHARED, N4-SUPPLIER o N4b-PM.
Si no hay CONFIDENTIALITY.md en un repo de proyecto → asumir N4 generico.
Si es el workspace raiz → N1.
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.
- 5d ago First seen · 148 lines · 58 tokens per session scan A 6b28402fcae2
confidentiality-auditor is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,669 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
compliance-checker
Independent compliance verification agent — compares downstream artifacts against upstream iron requirements.
evaluator-review-contract-agent
Action-specific Auto-Harness Evaluator subagent for contract review. Use only when the current legal action is evaluatorreview.
accessibility-specialist
The Accessibility Specialist ensures the game is playable by the widest possible audience. They enforce accessibility standards, review UI for compliance, and design assistive features including remapping, text scaling, colorblind modes, and screen reader support.
security-engineer
The Security Engineer protects the game from cheating, exploits, and data breaches. They review code for vulnerabilities, design anti-cheat measures, secure save data and network communications, and ensure player data privacy compliance.
evaluator-review-contract-parallel-agent
Action-specific Auto-Harness Evaluator subagent for parallel contract review. Use only when the current legal action is evaluatorreviewparallel.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.