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/autonomousWrote 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/autonomous)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/autonomous"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/autonomous/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/autonomous"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/autonomous.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 | $0.00070 | $0.07023 |
| Opus 5 | $0.00035 | $0.03512 |
| Sonnet 5 | $0.00014 | $0.01405 |
| Haiku 4.5 | $0.00007 | $0.00702 |
Grade A, and why
migrate-objects-auto 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 — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate Objects — Autonomous
On Entry IMPORTANT DO NOT SKIP
Tell the user:
Autonomous mode. I'll work the wave by giving each object its own subagent, which walks it the whole way — convert, deploy, tests, fixes — and I'll refill as they finish. I'll interrupt you only when an agent is stuck, when a dependency needs a human decision, and before any data moves. Say "stop" at any point and I'll let in-flight work land.
Step 0: Preflight
configure(project_dir=<project dir>, subagent_mode=true, snowflake_connection=<the configure connection the first prompt named>). Read the appended migration-status block. Bring the shared data infrastructure up:data_infrastructure(mode="up"). Relay itscost_reminder.status="not_ready"is not a green light — a first local bring-up runs every schema migration and can need more than one call, so follow itsremediationand callupagain until it reportsready. Once means one successful bring-up for the wave, not one call.- If
configure()reports setup is not finished, read ../../setup/SKILL.md then come back here.
subagent_mode attributes writes per Cortex conversation. Set it once here; it lasts the
life of the server and cannot be turned off. Cortex stamps identity on every MCP call —
do not pass agent_id. The parent hook injects 0000 while this latch is on: park a looping
object, reset a remediated transient failure, and relay non-terminal guidance.
Acknowledge unreviewed notes only in Step 3 (review), never in the dispatch
loop. Object-level outcomes stay parked for a person in an interactive session.
deploy, migrate_data, and validate_data are not binding-checked — keep
each agent on its own object.
Step 1: Ask how many subagents to run at once
Offer 2 / 4 / 6, recommend 4. State the
trade-off: more slots finish the wave faster, burn proportionally more tokens,
and produce more escalations competing for their attention. Call it N. Never
exceed it, and never quietly raise it.
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 · 527 lines · 0 tokens per session scan A e54fe6b690a5
migrate-objects-auto 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 70 tokens to every session and 7,023 once invoked, about $0.0003 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
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
record-gotchas
Capture surprises, workarounds, and rough edges hit while consuming the public surface of Prisma 8, Prisma Compute, or Prisma Postgres — anything a real user of these products would experience. Fires whenever an operator (or agent) writes a workaround, hits a surprising failure mode, or finds undocumented behaviour…
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
dingtalk-ai-table
Read and manage DingTalk AI table records through the DingTalk AI Table MCP. Use this skill when the user explicitly refers to a DingTalk AI table, fields, or records.
product-feature-tech-implement
A skill for delivering a product feature from a design document and existing source code through development, code review, and testing. It also creates a user guide and implementation summary.
write-prd
A product requirements document (PRD) writing skill that turns a product idea into a structured Markdown document with diagrams. A PRD describes what a product should do and the requirements needed to build it.