Saiku is an open-source semantic layer that represents data as analytical cubes for browser exploration, SQL queries, dashboards, and AI-agent access. It is for analysts and applications that need to query structured business data through Mondrian, Apache Calcite, REST, or MCP. The catalogue instruction helps agents work with Saiku.
Borrowing it
Nothing to install: this file belongs to spiculedata/saiku. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spiculedata/saiku/development/.github/prompts/review.mdgit clone --depth 1 https://github.com/spiculedata/saikuWrote 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/commands/spiculedata/saiku/review)<a href="https://agentmods.dev/commands/spiculedata/saiku/review"><img src="https://agentmods.dev/badge/commands/spiculedata/saiku/review/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/commands/spiculedata/saiku/review"><img src="https://agentmods.dev/badge/commands/spiculedata/saiku/review.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 | $0.00013 | $0.00455 |
| Opus 5.5 | $0.00005 | $0.00182 |
| Sonnet 5.5 | $0.00003 | $0.00091 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
review 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 26d 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.
What it actually says
Review pull request ${input:pr:PR number or URL} on spiculedata/saiku using the
rubric in docs/review-rubric.md. That rubric is the source of truth for the
axes, the severity labels, and the report shape — read it first and follow it
rather than improvising a checklist.
- Set up.
gh pr view <pr> --json title,body,baseRefName,filesandgh pr diff <pr>. ConfirmbaseRefNameisdevelopment. Readdocs/review-rubric.mdand the Conventions specific to this repo section ofAGENTS.md. - Claim check. List what the PR body promises; list what the diff actually contains. A mismatch is a blocking finding on its own.
- Walk the axes. Correctness and security first and in full, then tests, then repo conventions, then compatibility, then hygiene. Skip axes the diff cannot raise rather than padding the report.
- Verify locally where cheap. Run the module's suite
(
mvn -pl <module> -am test -Dtest=<Class>) for a behaviour claim, andcd saiku-ui && npm run check && npm testfor UI paths. Never lower.github/test-floors.jsonor.coverage-thresholds.jsonto make something pass. Do not push to the contributor's branch. - Report. Blocking findings first, then non-blocking, then praise. One line
per finding:
severity — file:line — what breaks — what you'd accept instead. End with a one-line verdict:approve,approve with comments, orchanges requested.
Do not merge, do not edit the PR body or the diff, and do not review a PR you
authored. The human maintainer has the final call — see CONTRIBUTING.md §
PR review.
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.
- 26d ago First seen · 32 lines · 13 tokens per session scan A 15c87d52b161
review is a command published in the GitHub repository spiculedata/saiku (1,334 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 455 once invoked, about $0.0001 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 2026-10-03.
Other commands, from other repositories
diff-review
Review a code diff in an editable HTML report with grounded findings.
fact-check
Check a document against the codebase and correct factual errors.
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.