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 skills add Bono12138/bonobox --skill query-supersetgit clone --depth 1 https://github.com/Bono12138/bonoboxWrote 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/skills/bono12138/bonobox/query-superset)<a href="https://agentmods.dev/skills/bono12138/bonobox/query-superset"><img src="https://agentmods.dev/badge/skills/bono12138/bonobox/query-superset/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/skills/bono12138/bonobox/query-superset"><img src="https://agentmods.dev/badge/skills/bono12138/bonobox/query-superset.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 | $0.00073 | $0.01338 |
| Opus 5 | $0.00036 | $0.00669 |
| Sonnet 5 | $0.00015 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
query-superset 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query Superset
Use scripts/superset_query.py as the only query implementation. This release supports Windows, username/password form login, and the legacy synchronous SQL Lab endpoint used by some Superset deployments. Do not claim support for SSO, MFA, API-token login, Power BI, or every Superset version.
1. Check compatibility before setup
Read references/capabilities.md. Confirm all of the following:
- the user is on Windows with Python 3.10 or newer;
- the user can open Superset and use SQL Lab with their own account;
- the deployment accepts username/password form login;
- the user knows the SQL Lab database connection ID and default schema;
- the organization allows the selected Agent and model to process the intended data.
If the deployment uses SSO, MFA, a custom login form, disables the legacy SQL Lab endpoint, or is not Superset, do not force it through the current client. Diagnose the boundary first. In a separate local branch, an Agent may make the smallest general adaptation or add a separate connector when it can do so without changing the enterprise platform or weakening authentication, TLS, VPN, or permissions. Test the original path and the new path. Record every outcome in a redacted compatibility Issue; prepare a linked Pull Request for a general, minimal, tested code change. If the Agent cannot adapt it safely, the Issue remains the useful result.
2. Configure without exposing credentials
Run in an interactive Windows terminal:
python scripts/superset_query.py configure
python scripts/superset_query.py auth
python scripts/superset_query.py status
python scripts/superset_query.py doctor
auth hides the password while it is typed and stores it with Windows DPAPI. Never ask the user to paste a password, cookie, CSRF token, or session into chat, a project file, an Issue, or Git.
doctor must execute a real SELECT 1. Do not describe the installation as working until it passes. Keep TLS verification enabled. If an internal certificate requires a CA bundle, configure the approved CA file rather than disabling verification.
What ships with it
4 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.
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.
- 12d ago First seen · 98 lines · 73 tokens per session scan A ca5aacbd8ade
query-superset is a skill published in the GitHub repository Bono12138/bonobox (5 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 1,338 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
jira-operations
JIRA cache and performance operations. TRIGGERS: 'warm the cache', 'warm cache', 'cache status', 'clear cache', 'cache warm', 'cache for project', 'discover project', 'project discovery', 'cache hit rate', 'optimize performance', 'rate limit'. Use for JIRA API performance optimization and project context discovery.…
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
python-logging-best-practices
Python logging with loguru, structlog, and orjson. TRIGGERS - loguru, structlog, structured logging.
clickhouse-architect
ClickHouse schema design and optimization. TRIGGERS - ClickHouse schema, compression codecs, MergeTree, ORDER BY tuning, partition key.