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/commands/gonzalezpazmonica/savia/audit-search)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/audit-search"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/audit-search/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/commands/gonzalezpazmonica/savia/audit-search"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/audit-search.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 | $0.00026 | $0.01093 |
| Opus 5 | $0.00013 | $0.00547 |
| Sonnet 5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
audit-search 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:
- audit-search — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Search — Búsqueda Contextual en Audit Trail
Propósito
Búsqueda flexible y poderosa en el audit trail usando lenguaje natural, filtros específicos, regex y saved searches. Útil para investigaciones, compliance checks y análisis históricos.
Sintaxis
/audit-search {query} [--from date] [--to date] [--user nombre] [--action tipo] [--lang es|en]
Parámetros
| Parámetro | Tipo | Descripción |
|---|---|---|
{query} |
string | Consulta: natural language, regex (/pattern/), o palabra clave |
--from |
date | Fecha inicio (YYYY-MM-DD) |
--to |
date | Fecha fin (YYYY-MM-DD) |
--user |
string | Filtrar por usuario (p.e. monica busca entradas de monica) |
--action |
string | Filtrar por tipo: query, modify, recommend, decision, generate |
--lang |
string | es (español), en (inglés) |
Ejemplos de Uso
Natural Language Search
/audit-search "cambios en el sprint 4"
# Busca entradas que mencionen sprint y cambios
/audit-search "quién creó el PBI de login"
# Busca acciones de creación de PBI con palabra "login"
/audit-search "recomendaciones rechazadas"
# Busca recomendaciones con resultado negativo
Regex Patterns
/audit-search "/sprint-[0-9]{4}-0[1-4]/"
# Busca cualquier sprint del 01 al 04
/audit-search "/pbi.*create.*success/"
# Busca creaciones exitosas de PBIs
/audit-search "/confidence:0\.[5-9][0-9]/"
# Busca entradas con confianza entre 50% y 99%
Filtros Específicos
/audit-search "error" --action modify --from 2026-03-01 --to 2026-03-02
# Busca errores en modificaciones entre esas fechas
/audit-search "sala-reservas" --user monica --action decision
# Decisiones tomadas por monica en sala-reservas
/audit-search "deprecated" --user * --action recommend
# Todas las recomendaciones que mencionan "deprecated"
Visualización de Resultados
Formato estándar (10-20 líneas):
🔍 Búsqueda: "cambios en sprint 4"
Período: sin filtro | Usuario: todos | Acción: todas
Resultados: 47 entradas encontradas
─ 2026-02-28 14:30 │ carlos │ /pbi-plan-sprint
Sprint: 2026-04 | Acción: 3 items priorización
Confianza: 92% | ✓ Éxito
─ 2026-02-27 09:15 │ monica │ /sprint-replan
Sprint: 2026-04 | Acción: redistribución capacidad
Confianza: 88% | ✓ Éxito
[Mostrando 2 de 47 — `/audit-search "cambios en sprint 4" --show-all` para ver todos]
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 · 149 lines · 26 tokens per session scan A 12391a895d93
audit-search is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,093 once invoked, about $0.0001 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 commands, from other repositories
research
Research a technical or product question.
build
Bulk-build ArcKit artefacts in parallel via subagent-orchestrated waves with resumable state.
recall
Search this machine's past AI coding sessions (deja-vu).
ghost
Show your ghost's current mood and happiness level.
commit
Read this skill before making git commits.
playground-create
Create a named playground HTML file and open it.