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 skills/delexw/claude-code-misc/ladybugdbnpx skills add delexw/claude-code-misc --skill ladybugdbgit clone --depth 1 https://github.com/delexw/claude-code-miscWhat 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 | $0.00173 | $0.01338 |
| Opus 5 | $0.00086 | $0.00669 |
| Sonnet 5 | $0.00035 | $0.00268 |
| Haiku 4.5 | $0.00017 | $0.00134 |
Grade C, and why
ladybugdb 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s https://install.ladybugdb.com | bash # Linux Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://install.ladybugdb.com | bash # Linux How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LadybugDB
LadybugDB is an embedded, in-process property graph database — no server process required. It uses the openCypher query language with a required, predefined schema (unlike Neo4j), columnar disk-based storage, vectorized query execution, and serializable ACID transactions.
Quick orientation
- Schema-first: you must create node/rel tables before inserting data
- One primary key per node table — automatically indexed, unique, non-null
- Walk semantics: repeated edges allowed in MATCH (unlike Neo4j's trail semantics)
- One write transaction at a time; multiple concurrent reads are fine
- In-memory mode: use
":memory:"as the database path for ephemeral databases
Installation
# CLI
curl -s https://install.ladybugdb.com | bash # Linux
brew install ladybug # macOS
# Python
pip install real_ladybug
# Node.js
npm install @ladybugdb/core
CLI basics
lbug mydb.lbug # open/create on-disk DB
lbug # in-memory (ephemeral)
lbug mydb.lbug < schema.cypher # batch mode
Key shell commands: :schema (show tables), :help, :quit, :mode [json|csv|markdown|...]
Reference files
Load only the sections you need:
| File | Contents |
|---|---|
references/cypher-reference.md |
DDL, DML, MATCH queries, transactions, macros, LadybugDB vs Neo4j differences |
references/python.md |
Python (real_ladybug) — connection, query, DataFrame, transactions |
references/nodejs.md |
Node.js (@ladybugdb/core) — connection, query, streaming, transactions |
references/java.md |
Java — Maven setup, connection, query, transactions |
references/rust.md |
Rust — Cargo setup, connection, query, Value types |
references/go.md |
Go — module setup, connection, query, transactions |
references/swift.md |
Swift — SPM setup, connection, query, async/await |
references/import.md |
COPY FROM, LOAD FROM, DataFrame import, cloud storage, performance tips |
references/export.md |
COPY TO, DataFrame export (pandas/polars/arrow), DuckDB export |
references/graph-algorithms.md |
PageRank, Louvain, WCC, SCC, K-Core, shortest paths — PROJECT_GRAPH |
references/vector-search.md |
HNSW index, CREATE/QUERY/DROP_VECTOR_INDEX, RAG pattern |
references/full-text-search.md |
BM25, CREATE/QUERY/DROP_FTS_INDEX, stemmers |
references/llm-embeddings.md |
CREATE_EMBEDDING — OpenAI, Ollama, Google, Bedrock, Voyage AI |
references/attach.md |
ATTACH/DETACH — PostgreSQL, DuckDB, SQLite, Delta Lake, Iceberg, Neo4j |
references/cli.md |
lbug shell flags, commands, output modes, batch/scripting mode |
references/explorer.md |
Ladybug Explorer Docker GUI — launch, env vars, volume mount |
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/attach.md 2.6 KB
- references/cli.md 2.7 KB
- references/cypher-reference.md 5.8 KB
- references/explorer.md 1.5 KB
- references/export.md 1.6 KB
- references/full-text-search.md 2.5 KB
- references/go.md 1.6 KB
- references/graph-algorithms.md 2.8 KB
- references/import.md 3.8 KB
- references/java.md 1.5 KB
- references/llm-embeddings.md 3.6 KB
- references/nodejs.md 1.7 KB
- references/python.md 2.5 KB
- references/rust.md 1.6 KB
- references/swift.md 1.7 KB
- references/vector-search.md 3.3 KB
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 · 95 lines · 173 tokens per session scan C 39f0c4efd42a
ladybugdb is a skill published in the GitHub repository delexw/claude-code-misc (1 stars, last pushed 5mo ago), licensed MIT. It adds 173 tokens to every session and 1,338 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
gpt-image-2
面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.
new
Create a new project to start development quickly.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…