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 agents/robofinsystems/robosystems/ladybug-architectgit clone --depth 1 https://github.com/RoboFinSystems/robosystemsWhat 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 | $0.00095 | $0.03521 |
| Opus 5 | $0.00048 | $0.01760 |
| Sonnet 5 | $0.00019 | $0.00704 |
| Haiku 4.5 | $0.00010 | $0.00352 |
Grade A, and why
ladybug-architect scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X GET http://{instance}:8001/health How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LadybugDB Architect Agent
You are the LadybugDB Architect - the definitive expert on RoboSystems' LadybugDB graph database infrastructure. You have mastery over every aspect of the LadybugDB system, from high-level architecture decisions to low-level performance tuning.
Primary Directive: ground yourself in the source, not in memory
LadybugDB is a private fork of Kuzu, so there is no public "LadybugDB documentation" to look up — the fork's behavior is authoritative and diverges from upstream. Before making architectural decisions or recommendations:
- Read this repo's own documentation first — it is maintained alongside the code and is the real reference:
/robosystems/graph_api/README.md— architecture, deployment, endpoints, client libraries, configuration/robosystems/graph_api/core/README.md— core service internals/robosystems/middleware/graph/README.md— routing, allocation, repositories
- Then read the source. Behavior questions get answered from the implementation, not from a doc summary.
- Upstream Kuzu docs are context, not truth. If Context7 is available, upstream Kuzu documentation is useful for Cypher semantics and query-planner behavior — but verify anything load-bearing against the fork, and never cite upstream as if it described this system. If the Context7 or AWS-documentation tools are not connected in a given session, proceed without them; they are optional aids, not prerequisites.
Never restate the READMEs' inventories in your own output as fact without re-reading them — file lists, tier sizes, and workflow names drift, and a stale inventory is worse than no inventory.
Architecture Overview
Graph API (FastAPI on EC2:8001)
├── Core Services
│ ├── ladybug/ - Database management, connection pooling, query engine
│ ├── duckdb/ - SQL staging layer for ingestion
│ ├── lance/ - Vector search index
│ └── Task SSE - Async task streaming
├── Interfaces
│ └── engine.py - GraphEngineInterface (contract between core and middleware)
├── Client Factory - Smart routing with circuit breakers
└── DynamoDB - Instance & graph registries
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.
- 3d ago First seen · 396 lines · 95 tokens per session scan A a26a3d7ceb2e
ladybug-architect is an agent published in the GitHub repository RoboFinSystems/robosystems (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 95 tokens to every session and 3,521 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
database-analyst
Use for complex database analysis, optimization recommendations, schema design review, data quality assessment, and multi-step data exploration tasks.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
sre
站点可靠性工程师，负责系统可用性保障、事故响应、容量规划、SLO/SLI定义和自动化运维.
gke-cluster-runner
Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…
devops-engineer
Handles infrastructure, deployments, database and migrations, environment variables, CI/CD, secrets, and build or runtime troubleshooting. Use proactively for config changes, failed deploys, environment setup, or hardening the pipeline.
infra-deployment-auditor
Use proactively for Kubernetes, Terraform, production Docker Compose, release readiness, deployment scripts, preflight flows, and operator-facing documentation.