query-performance

A method for measuring the real cost of ClickHouse database queries before they are merged. ClickHouse is a database designed for large-scale analytics.

In plain words
What is it for?
Use it when changing a data-access query, investigating a slow endpoint, or answering how a query will behave with larger datasets.
Why use it?
It replaces guesses about query speed and resource use with measurements, while checking that a changed query still returns the same results and order.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/comet-ml/opik/query-performance
Any agent
npx skills add comet-ml/opik --skill query-performance
Clone the repo
git clone --depth 1 https://github.com/comet-ml/opik

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,971 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00071 $0.01971
Opus 5 $0.00036 $0.00986
Sonnet 5 $0.00014 $0.00394
Haiku 4.5 $0.00007 $0.00197

Measured yesterday against content hash 406bfad0cf11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

query-performance 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 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.

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.

.agents/skills/query-performance/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query Performance Validation

Turn "this query looks expensive" into numbers a reviewer can act on. The output is a verdict per clause — change, keep, or caller's call — each attached to a measurement, plus the negative results so nobody retries them.

Ground rules

  1. Measure, never infer. Every claim needs a number that would differ if the claim were false.
  2. Equivalence gate first. No variant's cost is quotable until you have ensured it returns the same result as the query it varies, on every shape you measure. Where the query defines an order — anything with ORDER BY, and anything paginated, where order decides which rows land on the page — the comparison must include that order; compare order-independently only when the result genuinely has no defined order. A faster query that answers a different question is not an optimization. (Equivalence holds between the candidate and its variants. A candidate is often meant to change results versus main; main is the cost reference, not a result reference.)
  3. Collect the whole picture per run: latency, peak memory, CPU time, and what was scanned (parts, granules, marks, rows read). The first three are what the system pays; the scan numbers are the evidence that explains why they moved. A variant can read fewer rows and still cost more memory, more CPU and the same wall time — so no single number decides anything on its own.
  4. Two data shapes minimum, since rankings flip with density and skew. A win on one shape is a hypothesis.
  5. One variable per variant, including deleting a clause outright to see if it earns its keep.
  6. ≥5 runs; report p50, p90, p95 and min. Differences smaller than the spread are not differences, and the tail is where a polled endpoint hurts. Tail quantiles are only as good as the run count — if p90/p95 is what you are deciding on, run more than five.
  7. Write down what you could not measure — quotas, unreachable shapes, cache state. Those caveats bound the finding.

Read the full file on GitHub · 128 lines

Files

What ships with it

3 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.

Changes

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.

  1. yesterday First seen · 128 lines · 71 tokens per session scan A 406bfad0cf11

Subscribe to this mod's changes

query-performance is a skill published in the GitHub repository comet-ml/opik (21,685 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 1,971 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 2026-08-30.