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 Altinity/altinity-skills --skill altinity-profiler-clickhousegit clone --depth 1 https://github.com/Altinity/altinity-skillsWrote 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/altinity/altinity-skills/altinity-profiler-clickhouse)<a href="https://agentmods.dev/skills/altinity/altinity-skills/altinity-profiler-clickhouse"><img src="https://agentmods.dev/badge/skills/altinity/altinity-skills/altinity-profiler-clickhouse.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.06260 |
| Opus 5 | $0.00064 | $0.03130 |
| Sonnet 5 | $0.00026 | $0.01252 |
| Haiku 4.5 | $0.00013 | $0.00626 |
Grade A, and why
altinity-profiler-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 8d 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 — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job is to profile the target ClickHouse cluster via the MCP execute_query tool, then write out a
per-cluster <name>-analyst/ folder of 6 markdown files the user will save
as a new Skill (or use to overwrite an existing one).
Philosophy: knowledge base, not recipe book
The artifact is a knowledge base about the cluster — schema, engine
semantics, tenancy model, ingestion graph, observed access patterns,
declared vs. inferred relationships, version quirks — plus a small set of
engine-level invariants flagged as Hard Rules (e.g. "FINAL on AggMT is
the read idiom", "filter on (categoryid, brandid) first"). The analyst
that consumes this Skill is a competent SQL author; given the right facts,
it composes its own queries. Do not write canned SQL recipes for question
classes. Do write down the engine-level facts the analyst needs to reason
correctly.
A useful test: if a fact disappears from the artifact, would a competent analyst fail to write a correct query? If yes, the fact belongs. If no (it's just one of N plausible SQL shapes for the same question), it doesn't.
Anti-hallucination: every non-trivial claim must be verified
The profiler emits an artifact saved as a Skill and consumed later. Bad information compounds. Therefore: every fact in the artifact must either be verified by a cluster round-trip at profile time, or marked as inferred / unverified. No exceptions. Three claim types, three verification mechanics:
-
Existence claims — table X exists; column Y exists on table X; MV Z feeds table X. Verified by
system.tables/system.columns/system.tables.create_table_query. Cheap. Hard precondition: a table or column name does not appear in the artifact unless it was just queried back fromsystem. A fact that fails existence verification is dropped, not demoted. -
Behavior claims — this predicate prunes the primary index; FINAL on this table amplifies reads ~Nx; this skip index is used; this query shape is cheap on the captured tenant. Verified by
EXPLAIN indexes=1and a representativeSELECT … SETTINGS log_queries=1followed by asystem.query_loglookup keyed on a unique comment token. Behavior claims include the captured numbers (read_rows, granule prune ratio, latency) inline. A behavior claim with no captured measurement must be demoted to "inferred from schema".
What ships with it
12 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.
- .gitignore 78 B
- archetypes/A-plain-mt.md 2.6 KB
- archetypes/B-sharded-olap.md 4.3 KB
- archetypes/C-cube-mv.md 6.3 KB
- archetypes/D-star-dict.md 5.1 KB
- archetypes/E-streaming-fed.md 5.8 KB
- archetypes/README.md 6.3 KB
- edge-cases.md 19 KB
- pipeline.md 51 KB
- templates.md 34 KB
- tools/pareto_cut.py 10 KB runs code
- tools/synthesize_conventions.py 8.7 KB runs code
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.
- 8d ago First seen · 509 lines · 129 tokens per session scan A f336ab8b87c8
altinity-profiler-clickhouse is a skill published in the GitHub repository Altinity/altinity-skills (16 stars, last pushed 11d ago), licensed Apache-2.0. It adds 129 tokens to every session and 6,260 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…