Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflownpx agentmods add commands/bybren-llc/safe-agentic-workflow/local-deployWrote 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/bybren-llc/safe-agentic-workflow/local-deploy)<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/local-deploy"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/local-deploy/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/bybren-llc/safe-agentic-workflow/local-deploy"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/local-deploy.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 | $0.00008 | $0.02983 |
| Opus 5.5 | $0.00003 | $0.01193 |
| Sonnet 5.5 | $0.00002 | $0.00597 |
| Haiku 4.5 | $0.00001 | $0.00298 |
Grade B, and why
local-deploy scanned grade B 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo lsof -i :3000 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:3000/api/health | jq Copies of this mod
2 near-identical copies found in the catalogue:
- local-deploy — 97% identical, 48 lines differ
- local-deploy — 91% identical, 50 lines differ
How it starts
The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy the latest Docker image from GitHub Container Registry to your LOCAL machine's Docker. Works on any machine with Docker Desktop or Docker Engine installed.
Usage
/local-deploy # Deploy using dev mode (source-mounted, hot-reload)
/local-deploy --staging # Deploy using staging mode (self-contained, production-like)
/local-deploy --rebuild # Trigger GitHub Actions build first, then deploy
/local-deploy --staging --rebuild # Build and deploy to staging mode
Deployment Modes
| Mode | Flag | Container | Use Case |
|---|---|---|---|
| Development (default) | (none) | {{PROJECT_NAME}}-dev-app |
Active development with hot-reload (STANDARD port 3000) |
| Staging | --staging |
{{PROJECT_NAME}}-staging-app |
Production-like, self-contained, survives git operations (port 3001) |
| Both | --both |
Both containers | Run dev and staging simultaneously ({{TICKET_PREFIX}}-400/{{TICKET_PREFIX}}-401) |
When to use each mode:
- Dev mode: You're actively writing code and want hot-reload (STANDARD port 3000)
- Staging mode: Testing, demos, or when you need stability during git operations (port 3001)
- Both modes: Run both simultaneously for testing migrations, feature comparison, etc.
Workflow
1. Parse Arguments
Check flags:
# Check command arguments
if [[ "$*" == *"--staging"* ]]; then
MODE="staging"
else
MODE="development"
fi
if [[ "$*" == *"--rebuild"* ]]; then
REBUILD=true
else
REBUILD=false
fi
2. Pre-Deployment Status Check
Get current running status (check both container types):
# Check for staging container
docker ps --filter name={{PROJECT_NAME}}-staging-app --format '{{.Names}}\t{{.Status}}'
# Check for dev container ({{TICKET_PREFIX}}-400: updated container name)
docker ps --filter name={{PROJECT_NAME}}-dev-app --format '{{.Names}}\t{{.Status}}'
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.
- 1mo ago First seen · 471 lines · 8 tokens per session scan B ecce4c508329
local-deploy is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (425 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 2,983 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
deployment
Basic production deployment setup for FastAPI applications.
dare-docker-compose
Este comando analisa a arquitetura definida no BLUEPRINT.md e gera um docker-compose.yml completo com todos os serviços necessários (App, DB, Cache, etc).
dare-dockerfile
Este comando analisa a stack do projeto (definida no DESIGN.md ou .cursorrules) e gera um Dockerfile otimizado para produção e desenvolvimento.
dare-docker
Containerização DARE com Dockerfile e docker-compose seguros, performantes e idiomáticos. Multi-stage, usuário não-root, healthchecks, redes isoladas.
secure-flow-harden-dockerfile-fips
Transform your Docker images to FIPS compliant by removing root users and ensuring security best practices. Make all production docker images in this repository FIPS compliant by hardening Dockerfiles and ensuring they do not run as root users.
clarify
Reduce spec ambiguity via targeted questions with adaptive auto-invocation (planning is 80% of success).