Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sfc-gh-dflippo/snowflake-dbt-demonpx agentmods add skills/sfc-gh-dflippo/snowflake-dbt-demo/discover-extrasWrote 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/sfc-gh-dflippo/snowflake-dbt-demo/discover-extras)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/discover-extras"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/discover-extras/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/sfc-gh-dflippo/snowflake-dbt-demo/discover-extras"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/discover-extras.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 | $0.00113 | $0.05579 |
| Opus 5 | $0.00056 | $0.02789 |
| Sonnet 5 | $0.00023 | $0.01116 |
| Haiku 4.5 | $0.00011 | $0.00558 |
Grade A, and why
discover-extras 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover & Register Custom Assets
The conversion engine generates a known set of object types — tables, views, procedures, functions, SSIS packages, and so on. Real migrations almost always pull in other things that touch the same database: orchestration tools, BI assets, custom scripts, or object kinds the engine doesn't generate yet.
This step catches those and registers them in the registry as code units with kind=custom and a free-form customKind discriminator (any string outside the reserved Kind enum), so the orchestration layer tracks them alongside built-in units.
On Entry
The setup machine only routes here after the user has said they have assets the engine doesn't generate (last setup step, after assessment and — if they opted in — the post-assessment migration setup), so don't re-ask that. Open with:
Discover custom assets. Let's get them tracked. I'll go category by category and register what you list, so each one shows up alongside the rest of your migration.
If the user has already registered some custom units (migration_status shows units with kind=custom), surface the count first:
"You've already registered N custom units (customKinds: ). Want to add more, or call this done?"
Step 1: Pick Categories
Use ask_user_question (multi-select) with these top categories. Keep the list at five and let the auto-appended "Something else" cover the long tail:
"Which of these apply to your project? (multi-select)"
- Orchestration / data movement — FiveTran, Airflow, Informatica, Talend, ADF, Glue
- BI / analytics layer — SSAS cubes, Tableau extracts, Looker views, dbt models
- Engine doesn't generate yet — Oracle PACKAGE/PACKAGE BODY, SQL Server triggers, sequences, edge cases
- Hand-maintained scripts — bash/PowerShell jobs, cron tasks, manual deployment scripts
- Nothing after all — I was wrong upstream, move on
If the user picks Nothing after all, jump to Step 4 and mark the step done — that records the step as answered so it isn't put to them again.
What ships with it
2 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.
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.
- 2d ago First seen · 294 lines · 113 tokens per session scan A 22ddb5c5ed8a
discover-extras is a skill published in the GitHub repository sfc-gh-dflippo/snowflake-dbt-demo (33 stars, last pushed 3d ago), licensed Apache-2.0. It adds 113 tokens to every session and 5,579 once invoked, about $0.0006 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 2026-09-10.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…