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 agentmods add commands/alphaaiservice/cortex/gen-infragit clone --depth 1 https://github.com/alphaaiservice/cortexWrote 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/alphaaiservice/cortex/gen-infra)<a href="https://agentmods.dev/commands/alphaaiservice/cortex/gen-infra"><img src="https://agentmods.dev/badge/commands/alphaaiservice/cortex/gen-infra.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.18235 |
| Opus 5 | $0.00025 | $0.09118 |
| Sonnet 5 | $0.00010 | $0.03647 |
| Haiku 4.5 | $0.00005 | $0.01824 |
Grade C, and why
gen-infra scanned grade C with 2 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
&& rm -rf /var/lib/apt/lists/* Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Nginx | `nginx:1.25-alpine` | 80/443 | `curl localhost` | How it starts
The opening of the file, as written. The whole thing — 2,193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infrastructure as Code Generator
Target: $ARGUMENTS
Parse $ARGUMENTS to extract:
- Infrastructure type:
docker|k8s|k3s|terraform|helm(default:docker) - Environment:
--env=development|--env=staging|--env=production(default:development)
If $ARGUMENTS is empty, default to docker --env=development.
Step 1: Detect Application Services
Scan the project to identify all services. Run these in parallel using Agent tool (mode = "bypassPermissions"):
Scan 1: Backend Detection
echo "=== Python/FastAPI Backend ==="
ls -la app/ src/ backend/ 2>/dev/null
cat requirements*.txt pyproject.toml setup.py 2>/dev/null | head -100
echo ""
echo "=== Node.js/NestJS Backend ==="
ls -la src/main.ts nest-cli.json 2>/dev/null
cat package.json 2>/dev/null | grep -E "nestjs|@nestjs" | head -20
echo ""
echo "=== Java/Spring Boot Backend ==="
ls -la build.gradle.kts pom.xml src/main/java 2>/dev/null
cat build.gradle.kts 2>/dev/null | head -50
echo ""
echo "=== Dockerfile ==="
ls -la Dockerfile docker/Dockerfile 2>/dev/null
echo ""
echo "=== Node/Next.js Frontend ==="
ls -la frontend/ web/ client/ next.config* package.json 2>/dev/null
cat package.json 2>/dev/null | head -50
Scan 2: Database & Services Detection
echo "=== Database Configs ==="
grep -rn "mysql\|MySQL\|asyncmy\|sqlalchemy" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -10
grep -rn "mongo\|MongoDB\|beanie\|motor\|pymongo" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -10
grep -rn "redis\|Redis" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -10
echo ""
echo "=== Additional Services ==="
grep -rn "meilisearch\|MeiliSearch" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -5
grep -rn "celery\|Celery" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -5
grep -rn "minio\|MinIO\|S3\|boto3" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -5
grep -rn "qdrant\|Qdrant" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -5
grep -rn "langfuse\|Langfuse" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -5
grep -rn "flower" . --include="*.py" --include="*.toml" --include="*.txt" -l 2>/dev/null | head -5
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.
- 4d ago First seen · 2,193 lines · 50 tokens per session scan C 004884cf34b5
gen-infra is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 28d ago), licensed MIT. It adds 50 tokens to every session and 18,235 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
_composicion
Protocolo interno compartido para la composición dinámica del equipo de Alfred según tarea, stack y señales runtime.
feature
Ciclo completo de desarrollo: producto, arquitectura, desarrollo, QA, docs, entrega.
lucius
Segunda opinión técnica externa vía Codex CLI — diagnóstico y prescripción por ítem.
next
Decide el siguiente paso operativo y lo ejecuta si es inequívoco.
spike
Investigación técnica sin compromiso de implementación.
uat
Prepara o registra la UAT del entregable actual. Antes /alfred-dev:verify.