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/kivo360/OmoiOSWrote 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/rules/kivo360/omoios/development)<a href="https://agentmods.dev/rules/kivo360/omoios/development"><img src="https://agentmods.dev/badge/rules/kivo360/omoios/development/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/rules/kivo360/omoios/development"><img src="https://agentmods.dev/badge/rules/kivo360/omoios/development.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 | $0.00000 | $0.00466 |
| Opus 5.5 | $0.00000 | $0.00186 |
| Sonnet 5.5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
development 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 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.
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
Backend Development Mode
Starting the Development Environment
To run the backend services with hot-reload during development:
# From the project root directory
just watch
This command:
- Starts PostgreSQL and Redis containers
- Builds and runs the API, Worker, and Orchestrator services
- Enables hot-reload via
docker compose watch- changes to Python files automatically restart services
Service Architecture
The just watch command runs these services:
- backend: FastAPI server (port 8000)
- worker: Background task worker
- postgres: PostgreSQL database (port 15432)
- redis: Redis cache (port 16379)
The orchestrator loop runs inside the backend service and:
- Polls for pending tasks every 10 seconds
- Spawns Daytona sandboxes (when
DAYTONA_SANDBOX_EXECUTION=true) - Logs heartbeats every 30 seconds (JSON format via structlog)
Viewing Logs
# All services
docker compose logs -f
# Specific service
docker compose logs -f backend
# Filter orchestrator JSON logs with jq
docker compose logs backend 2>&1 | grep -E '^\{' | jq 'select(.event == "heartbeat")'
Common Issues
"too many clients already" (PostgreSQL)
Connection pool exhaustion. Restart services:
docker compose restart postgres
# or full restart
docker compose down && just watch
Multiple Alembic Heads
cd backend
uv run alembic heads # Check for multiple heads
uv run alembic merge <head1> <head2> -m "merge_heads"
Important Paths
- Justfile:
/senior_sandbox/Justfile(main commands) - Docker Compose:
/senior_sandbox/backend/docker-compose.yml - Orchestrator Worker:
/senior_sandbox/backend/omoi_os/workers/orchestrator_worker.py
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 · 71 lines · 0 tokens per session scan A cc75dbe291bf
development is a cursor rule published in the GitHub repository kivo360/OmoiOS (81 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 466 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
websocket-patterns
WebSocket endpoints, connection limits, and broadcast helpers.
email-and-misc-utils
Email service, resume parser, BYOK encryption utilities.
google-oauth
Google OAuth configuration, secure auth flow, CSRF state, exchange-code pattern.
security-middleware
Security headers, CORS, global rate limiting, middleware order.
python-conventions
Python coding style, FastAPI endpoint template, code organisation sections.
rolemule-core
Core RoleMule conventions — app name, error system, JSON serialization, background tasks.