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/monoes/monomindWrote 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/monoes/monomind/okf-import)<a href="https://agentmods.dev/commands/monoes/monomind/okf-import"><img src="https://agentmods.dev/badge/commands/monoes/monomind/okf-import/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/monoes/monomind/okf-import"><img src="https://agentmods.dev/badge/commands/monoes/monomind/okf-import.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 | $0.00017 | $0.00209 |
| Opus 5.5 | $0.00007 | $0.00084 |
| Sonnet 5.5 | $0.00003 | $0.00042 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
okf-import 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 yesterday.
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.
What it actually says
Parse $ARGUMENTS for:
--scope <name>or-s <name>→ knowledge scope (default:shared)--globalor-g→ import into the personal cross-project global brain- Remaining positional arg → bundle directory path (REQUIRED)
If no bundle directory provided, ask: "Which directory contains the OKF bundle to import?"
Run the import:
npx monomind doc import "<bundle_dir>" -s "<scope>"
Use doc import, never doc ingest — plain ingest would index the bundle's own
index.md manifest as if it were knowledge. Add --global when restoring a personal
brain exported with doc export --global.
After completion, report files processed, chunks indexed, and any errors. If the bundle directory doesn't exist or contains no .md files, say so.
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.
- yesterday First seen · 23 lines · 17 tokens per session scan A eb44e2fe8610
okf-import is a command published in the GitHub repository monoes/monomind (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 209 once invoked, about $0.0001 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 2026-10-26.
Other commands, from other repositories
ordenar
Grupo: Trabajo con el framework En una frase: Capturar archivos, carpetas y dumps del chat — documentar en la capa correcta y dejar manifest recuperable. Cuándo: Volcás mucha data, briefs, notas o paths y querés que el DT clasifique, documente e indexe para reutilizar. Quién: Cualquier operador del repo.
verificar
Grupo: Trabajo con el framework En una frase: Verificar números de planillas y reportes con script, sin cálculo mental de la IA. Cuándo: Compartís una planilla/reporte o pedís totales, sumas o reconciliación de cifras. Quién: Cualquier operador del repo.
cerebro-work
Grupo: Módulos del segundo cerebro En una frase: Sync cerebro profesional — atajo CerebroWork (script en raíz). Cuándo: Querés correr el sync Meet→Markdown sin recordar paths; ritual rápido post-OAuth. Quién: Cualquier operador del repo.
drive
Grupo: Rutina del día a día En una frase: Conectar Drive (plugin oficial) y elegir carpetas como contexto. Solo lectura. Cuándo: Primera vez que querés consultar documentos en Drive con el DT; o para cambiar qué carpetas compartís. Quién: Cualquier operador del repo.
sincronizar-notas-meet
Grupo: Módulos del segundo cerebro En una frase: Exportar notas Gemini (.gdoc) a Markdown local en el cerebro. Cuándo: Hay reuniones nuevas en Drive o falta contenido en el espejo .md. Quién: Cualquier operador del repo.
doctor
Health-check the harness: kernel load, MCP wiring, memory backend, host adapter.