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 CATWILLgh/MAINFRAME --skill mainframe-clickhousegit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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/catwillgh/mainframe/mainframe-clickhouse)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-clickhouse"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-clickhouse/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/catwillgh/mainframe/mainframe-clickhouse"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-clickhouse.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 | $0.00039 | $0.00725 |
| Opus 5.5 | $0.00016 | $0.00290 |
| Sonnet 5.5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
mainframe-clickhouse 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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use ClickHouse within a verified boundary
Before connecting, resolve the endpoint, routing or tunnel, intended environment,
database/table, credential identity, and requested operation from applicable
project configuration and caller authority. A credential permits authentication;
it does not authorize an operation. Use mainframe-infrastructure for broader
deployment coordination and mainframe-secrets for credential delivery when
available. Do not print credentials or dump connection configuration.
Establish the boundary before executing SQL:
| Target | Operating boundary |
|---|---|
| Production | Scoped authorized reads with resource bounds; changes require authority for the exact operation and an adequate recovery boundary. |
| Shared staging/test | Preserve other users, persistent data, and shared capacity. Test naming does not authorize resets. |
| Verified disposable fixture | Create, change, or remove only the resources covered by explicit disposal authority; use representative tests without unnecessary production ceremony. |
| Unknown or conflicting identity | Do not write, reset, or run an expensive query. Resolve identity through configuration and the smallest permitted metadata read; continue offline work. |
Loopback addresses, local clients, containers, SSH tunnels, a database named
test, and a read-only account do not prove a disposable server. Verify the
actual destination and storage ownership. A separate test schema on a production
cluster still shares production resources. Reuse established authority; do not
ask again merely because the operation is sensitive. Do not invent ClickHouse
disposal permission from a policy covering another database.
Read only the relevant method
| Current decision | Read |
|---|---|
| Target ambiguity, environment classification, or permission boundary | Target and authority |
| SQL analysis, diagnostics, query correctness, or resource limits | Safe queries |
| Ingestion, retries, schema, updates, deletes, or cluster-wide changes | Writes and schema |
| Capacity, maintenance, incident cancellation, backup, or restore | Operations and recovery |
| Version-sensitive syntax, settings, engine behavior, or missing details | Official source map, then applicable current documentation |
What ships with it
5 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.
- 9d ago First seen · 60 lines · 39 tokens per session scan A efec57fed122
mainframe-clickhouse is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 725 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-07.
Other skills, from other repositories
cmux-backend
Backend TypeScript and Cloud VM development rules for cmux. Use when editing web/app/api, web/services, backend scripts, Cloud VM lifecycle, provider integrations, Postgres, Stack Auth pricing gates, migrations, or provider image build scripts.
db-sculptor
Design database schemas with Prisma/Drizzle, PostgreSQL index strategy (B-tree, GIN, GiST, BRIN, Hash), query optimization (EXPLAIN ANALYZE), migration safety (expand/contract, zero-downtime), and sharding/partitioning. Use when user asks to design schema, create migrations, optimize slow queries, add indexes, choose…
neon-postgres
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related…
chromadb
Manage the ChromaDB vector database that stores the ecosystem's persistent memory. Use when user asks to check memory storage, backup memory, search stored entries, delete entries, or reset the vector database. Do NOT use for general question answering about past sessions (use the memory skill for that).
db-admin
PostgreSQL database administration — backup/restore (pgdump, PITR, WAL archiving), health monitoring (connections, bloat, cache hit ratio, dead tuples), connection pooling (PgBouncer), replication (streaming, logical), vacuum/autovacuum tuning, and scheduled backups with retention. Use when user asks to backup a…
rp1-migrate
Safely migrate legacy rp1 project artifacts to the current layout.