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 databricks-solutions/ai-dev-kit --skill testgit clone --depth 1 https://github.com/databricks-solutions/ai-dev-kitWrote 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/databricks-solutions/ai-dev-kit/test)<a href="https://agentmods.dev/skills/databricks-solutions/ai-dev-kit/test"><img src="https://agentmods.dev/badge/skills/databricks-solutions/ai-dev-kit/test/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/databricks-solutions/ai-dev-kit/test"><img src="https://agentmods.dev/badge/skills/databricks-solutions/ai-dev-kit/test.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 | $0.00080 | $0.01976 |
| Opus 5.5 | $0.00032 | $0.00790 |
| Sonnet 5.5 | $0.00016 | $0.00395 |
| Haiku 4.5 | $0.00008 | $0.00198 |
Grade A, and why
skill-test 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 2mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 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.
- baselines/databricks-agent-bricks/baseline.yaml 521 B
- baselines/databricks-aibi-dashboards/baseline.yaml 478 B
- baselines/databricks-apps-python/baseline.yaml 328 B
- baselines/databricks-bundles/baseline.yaml 1002 B
- baselines/databricks-genie/baseline.yaml 710 B
- baselines/databricks-model-serving/baseline.yaml 4.2 KB
- baselines/databricks-python-sdk/baseline.yaml 1.4 KB
- baselines/databricks-spark-declarative-pipelines/baseline.yaml 553 B
- baselines/databricks-synthetic-data-gen/baseline.yaml 521 B
- baselines/databricks-zerobus-ingest/baseline.yaml 853 B
- CUSTOMIZATION_GUIDE.md 8.8 KB
- eval-criteria/general-quality/SKILL.md 1.4 KB
- eval-criteria/sql-correctness/references/DATABRICKS_SQL_PATTERNS.md 1.4 KB
- eval-criteria/sql-correctness/SKILL.md 1.7 KB
- eval-criteria/tool-selection/references/MCP_TOOL_GUIDE.md 2.2 KB
- eval-criteria/tool-selection/SKILL.md 2.0 KB
- install_skill_test.sh 3.6 KB runs code
- notebooks/gepa_skill_optimization_demo.ipynb 24 KB
- pyproject.toml 987 B
- README.md 22 KB
- references/python-api.md 4.7 KB
- references/scorers.md 3.9 KB
- references/trace-eval.md 5.7 KB
- references/workflows.md 6.9 KB
- references/yaml-schemas.md 3.5 KB
- scripts/_common.py 3.0 KB runs code
- scripts/add_example.py 8.1 KB runs code
- scripts/add.py 3.5 KB runs code
- scripts/baseline.py 920 B runs code
- scripts/generate_examples.py 15 KB runs code
- scripts/generate_ground_truth.py 22 KB runs code
- scripts/init_skill.py 966 B runs code
- scripts/list_traces.py 2.4 KB runs code
- scripts/mlflow_eval.py 3.1 KB runs code
- scripts/optimize.py 17 KB runs code
- scripts/regression.py 1.0 KB runs code
- scripts/review.py 2.0 KB runs code
- scripts/routing_eval.py 1.2 KB runs code
- scripts/run_app_eval.py 15 KB runs code
- scripts/run_eval.py 1.0 KB runs code
- scripts/scorers_update.py 2.6 KB runs code
- scripts/scorers.py 887 B runs code
- scripts/sync.py 1.1 KB runs code
- scripts/trace_eval.py 4.8 KB runs code
- scripts/trace_to_examples.py 25 KB runs code
- skills/_routing/ground_truth.yaml 7.9 KB
- skills/_routing/manifest.yaml 442 B
- skills/databricks-agent-bricks/candidates.yaml 15 B
- skills/databricks-agent-bricks/ground_truth.yaml 20 KB
- skills/databricks-agent-bricks/manifest.yaml 2.1 KB
- skills/databricks-aibi-dashboards/candidates.yaml 15 B
- skills/databricks-aibi-dashboards/ground_truth.yaml 4.6 KB
- skills/databricks-aibi-dashboards/manifest.yaml 4.7 KB
- skills/databricks-apps-python/candidates.yaml 150 B
- skills/databricks-apps-python/ground_truth.yaml 17 KB
- skills/databricks-apps-python/manifest.yaml 1.1 KB
- skills/databricks-bundles/candidates.yaml 192 B
- skills/databricks-bundles/ground_truth.yaml 38 KB
- skills/databricks-bundles/manifest.yaml 1.2 KB
- skills/databricks-config/ground_truth.yaml 6.0 KB
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.
- 2mo ago First seen · 206 lines · 80 tokens per session scan A 8d36c5052fb8
skill-test is a skill published in the GitHub repository databricks-solutions/ai-dev-kit (1,974 stars, last pushed 6d ago), with no licence file. It adds 80 tokens to every session and 1,976 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cast-verify
Prove the work before calling it done, and leave the evidence where reviewers read it. Runs the repository's checks, exercises the change in the human's own browser or on the command line, captures screenshots or output, attaches them to the task and the thread, and only then marks the work done. Use before declaring…
e2e-check
Run E2E tests or interactive browser verification. Triggers on: 'run e2e', 'e2e test', 'browser test', 'check in browser', 'verify UI', 'interactive test'.
tdd
Test-driven development, from unit to end-to-end tests. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration or end-to-end tests (Playwright, Cypress). Don't use to backfill tests on existing code (/refactor) or diagnose an unknown bug (/debug).
test-check
MUST use after implementing new features or bug fixes, when user asks 'run the tests', 'are tests passing?', 'test this', or before any deployment step. Also trigger when tests were previously failing and fixes were applied.
check
Validate code quality — auto-fix formatting/lint, verify types, run tests. Use when asked to "validate code", "check code", or validate before committing; also lint-only asks ("run linter", "fix lint errors"). Don't use for committing (/commit), pushing (/to-pr), or writing new tests (/tdd).
refactor
Improve existing code without changing behavior — split large functions, backfill tests, simplify. Use when asked to "refactor", "add missing tests", "split functions", "simplify", "clean up code", or "reduce complexity". Don't use for new features (/tdd), security hardening (/harden), or PR review (/code-review).