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 agentmods add rules/datahub-project/datahub/test-reviewgit clone --depth 1 https://github.com/datahub-project/datahubWhat 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 | $0.00022 | $0.00221 |
| Opus 5 | $0.00011 | $0.00111 |
| Sonnet 5 | $0.00004 | $0.00044 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
test-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 3d 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
DataHub Test Review
When asked to review tests, check test quality, validate smoke tests, or review integration tests,
follow the skill instructions in .agent-skills/test-review/SKILL.md.
Quick reference
- Load standards from
.agent-skills/test-review/standards/smoke-and-integration.md - If a PR number is given, use incremental review mode with
.agent-skills/test-review/scripts/detect-test-changes.sh - Otherwise, gather test files and run a full review
- Use the sequential fallback workflow (read each file, check against standards, report findings)
- Generate a report using templates from
.agent-skills/test-review/templates/
Scope
- In scope:
smoke-test/(Python smoke tests + Cypress integration tests) - Out of scope:
metadata-ingestion/tests/unit/, connector-specific integration tests
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.
- 3d ago First seen · 24 lines · 22 tokens per session scan A fe36ee23278c
test-review is a cursor rule published in the GitHub repository datahub-project/datahub (12,629 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 221 once invoked, about $0.0001 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 cursor rules, from other repositories
sdrf-skills
Structured skills for expert-level SDRF (Sample and Data Relationship Format) annotation in proteomics.
git
Never mutate git history, remotes, or GitHub repo state.
css
TSF stylesheet conventions, layout debugging, and minification.
javascript
TSF JavaScript syntax, formatting, and minification.
local
Private workspace guidance and gitignored .local search (Grep/Glob are blind).
docs
Readme wording constraints, WordPress readme format, changelog prose style, and public API naming requirements.