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 i9wa4/dotfiles --skill data-platformgit clone --depth 1 https://github.com/i9wa4/dotfilesWrote 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/i9wa4/dotfiles/data-platform)<a href="https://agentmods.dev/skills/i9wa4/dotfiles/data-platform"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/data-platform/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/i9wa4/dotfiles/data-platform"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/data-platform.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 | $0.00043 | $0.00492 |
| Opus 5.5 | $0.00017 | $0.00197 |
| Sonnet 5.5 | $0.00009 | $0.00098 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
data-platform 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 1mo 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
Data Platform
Owns repo-local data-platform guardrails. These references are self-contained for local safety and workflow rules; broad provider skill packs are reference-only unless deliberately promoted into the active runtime bundle.
1. Scope
- BigQuery cost-aware query patterns, GoogleSQL guardrails, table design, and slot usage checks.
- Databricks Queries API, VARIANT/JSON patterns, dashboard API notes, dbt integration, and Jupyter kernel execution.
- Local dbt target setup and Databricks SQL dialect caveats.
- Restricted BigQuery/dbt safety workflows that keep local runs out of production schemas.
- Cloud authentication workflows that must run through a user-authenticated pane instead of the agent pane.
Out of scope:
- Agent harness runtime, Home Manager agent config, hooks, postman routing, or
installed agent outputs; use
dotfiles. - GitHub issue, PR, review, or public-surface mechanics; use
dev-platform-workflow. - Diagram authoring or export workflows; use
diagramming. - Generic Bash, Python, Nix, Markdown, or implementation-loop work; use
programming.
2. Workflow
- Inspect the relevant files, current repo conventions, and
git status. - Select the focused reference below before changing files or running data commands.
- For any command that can write cloud or warehouse state, verify the target, schema, and approval requirements before execution.
- Keep repo-local safety constraints in focused references and keep the owner skill as the primary trigger surface.
- Run the fastest focused check during iteration, then the nearest repo validation surface before reporting success.
3. References
What ships with it
11 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.
- evals/eval.yaml 514 B
- evals/tasks/negative-trigger-1.yaml 410 B
- evals/tasks/positive-trigger-1.yaml 405 B
- evals/tasks/positive-trigger-2.yaml 419 B
- examples/staging-model.sql 352 B
- references/bigquery.md 1.5 KB
- references/cloud-auth.md 1.1 KB
- references/databricks.md 3.9 KB
- references/dbt.md 1.7 KB
- references/restricted-bigquery-dbt.md 1.5 KB
- scripts/databricks-libs.py 6.3 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.
- 1mo ago Changed · +1 lines 1a9a1dbcec3e
- 2mo ago First seen · 56 lines · 43 tokens per session scan A daf74548c5c9
data-platform is a skill published in the GitHub repository i9wa4/dotfiles (12 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 492 once invoked, about $0.0002 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
merge-pr
Merge a pull request with status checks, squash merge, and branch cleanup. Handles worktree contexts.
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
gui-debug
Verify a rendering or window-chrome change in any macOS GUI app unattended — find its CGWindowID via JXA, capture that window alone (with per-pixel alpha) using screencapture -l, read exact RGBA via NSBitmapImageRep, and synthesize keystrokes, chords, clicks and drags with CGEventPost. Use for…
audit
Repo audits, one mode or all (codebase, docs, process, perf, tests, threat-model, motion, SEO, debt). Triggers "audit the codebase", "full audit", "perf audit", "audit the tests", "threat model", "motion audit", "seo audit", "debt ledger".
self-review
Deliberate end-to-end review pass over a completed change, applying the laziness ladder. Invoke when the user asks for a review, or when orchestrating one. Not a routine step after every edit.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…