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/migrate-objectsWrote 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/migrate-objects)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-objects"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-objects/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/migrate-objects"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-objects.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 | $0.00045 | $0.03213 |
| Opus 5 | $0.00023 | $0.01606 |
| Sonnet 5 | $0.00009 | $0.00643 |
| Haiku 4.5 | $0.00005 | $0.00321 |
Grade A, and why
migrate-objects 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate Objects
Prerequisite: Support Level Check
Check support from the configure() response.
If support is basic, load BASIC_SUPPORT.md and STOP. Do not continue with the steps below.
On Entry IMPORTANT DO NOT SKIP
Tell the user:
Phase 2: Migrate Objects. Now we'll deploy your objects to Snowflake according to your wave plan (if you created one in assessments). Each object goes through a deploy-test-fix loop.
Step 1: Confirm setup is finished
The Snowflake target (connection + database) and the testing path are
configured by the setup state machine, not here — they're the last
steps of setup, gated behind the post-assessment continueToMigration
prompt. A user who stopped at assessment has none of them yet.
Call progress_setup().
completed: true→ setup is finished; continue to Step 2.- Anything else (a
next_task/next_promptcame back) → setup isn't done. Load../setup/SKILL.mdand drive it to completion, then come back. Don't ask for a connection, database, or testing preference yourself — the machine owns those questions and persists the answers.
This is also the path for a user who answered "Not now" at the gate and has since changed their mind: the prompt is re-offered, and answering "Yes" walks them through the Snowflake target and testing setup.
Advancing and reporting
This rule is the same for every task in the loop below — deploy, test, capture, seed, fix, validate:
- Do the task's work as its skill describes.
- Ask what's next. Re-pull
migration_status(mode="my_objects_summary")(ormigration_status(mode="next_task", object_id="<id>")for one object). The machine advances you when it can see the work is done — a tool wrote the registry field, the object exists in Snowflake, or the expected file exists. - Call
transition_statusto report or override:- a failure you can't fix —
transition_status(status='advance', task='<task>', outcome='failed', error='<sql|infra>'); - an outcome the system can't observe and you had to judge — e.g. "all tests passed" (migrate-object/RUN_TESTS.md), view parity (migrate-object/VALIDATE_VIEW.md), ETL stabilization (migrate-etl/SKILL.md);
- an override —
bypassa precondition,resetan errored task, orskip.
- a failure you can't fix —
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.
- actions/claim_objects.md 3.7 KB
- actions/data-migration/references/background-monitoring.md 7.9 KB
- actions/data-migration/references/extraction-strategies-reference.md 7.0 KB
- actions/data-migration/references/iceberg-setup-reference.md 14 KB
- actions/data-migration/references/task-model-reference.md 8.2 KB
- actions/data-migration/references/troubleshooting-reference.md 23 KB
- actions/data-migration/references/workflow-config-reference.md 30 KB
- actions/data-migration/RUN.md 2.9 KB
- actions/data-migration/SKILL.md 34 KB
- actions/etl-aifirst/evals/README.md 5.8 KB
- actions/etl-aifirst/evals/trigger-baseline-result.json 7.4 KB
- actions/etl-aifirst/evals/trigger-eval-set.json 7.8 KB
- actions/etl-aifirst/platforms/AUTHORING_CONTRACT.md 8.3 KB
- actions/etl-aifirst/platforms/platform_adf.json 33 KB
- actions/etl-aifirst/platforms/platform_alteryx.json 55 KB
- actions/etl-aifirst/platforms/platform_datastage.json 72 KB
- actions/etl-aifirst/platforms/platform_informatica.json 38 KB
- actions/etl-aifirst/platforms/platform_pentaho.json 50 KB
- actions/etl-aifirst/platforms/platform_ssis.json 40 KB
- actions/etl-aifirst/platforms/README.md 1014 B
- actions/etl-aifirst/producer/AiFirstProducerDataFlowContext.cs 27 KB
- actions/etl-aifirst/producer/AiFirstProducerIrHydrator.cs 27 KB
- actions/etl-aifirst/producer/AiFirstSsisSemanticsShim.cs 17 KB
- actions/etl-aifirst/producer/build.sh 1.3 KB runs code
- actions/etl-aifirst/producer/CallableMigrator.csproj 6.7 KB
- actions/etl-aifirst/producer/CapturingLogger.cs 1.6 KB
- actions/etl-aifirst/producer/DialectPlatform.cs 3.7 KB
- actions/etl-aifirst/producer/NoOpEtlSqlProcessor.cs 2.9 KB
- actions/etl-aifirst/producer/NoOpServices.cs 8.6 KB
- actions/etl-aifirst/producer/NoOpSqlValueMigrator.cs 4.8 KB
- actions/etl-aifirst/producer/ProducerOrchestration.cs 15 KB
- actions/etl-aifirst/producer/ProducerReportHarness.cs 15 KB
- actions/etl-aifirst/producer/ProducerReports.cs 49 KB
- actions/etl-aifirst/producer/Program.cs 62 KB
- actions/etl-aifirst/producer/README.md 957 B
- actions/etl-aifirst/producer/RecordingEtlAssessmentBuilder.cs 5.6 KB
- actions/etl-aifirst/producer/tests/ReconciliationTests.cs 5.2 KB
- actions/etl-aifirst/producer/tests/ReconciliationTests.csproj 2.2 KB
- actions/etl-aifirst/pyproject.toml 331 B
- actions/etl-aifirst/scripts/ai_fill.py 14 KB runs code
- actions/etl-aifirst/scripts/aifirst-migrate.sh 83 KB runs code
- actions/etl-aifirst/scripts/alteryxdoc.py 9.4 KB runs code
- actions/etl-aifirst/scripts/author_platform_table.py 56 KB runs code
- actions/etl-aifirst/scripts/coverage_gate.py 31 KB runs code
- actions/etl-aifirst/scripts/docmodel.py 10 KB runs code
- actions/etl-aifirst/scripts/dsxdoc.py 14 KB runs code
- actions/etl-aifirst/scripts/emit_sources_yml.py 3.9 KB runs code
- actions/etl-aifirst/scripts/emit.py 128 KB runs code
- actions/etl-aifirst/scripts/etl_elements_census.py 11 KB runs code
- actions/etl-aifirst/scripts/execute_gate.py 34 KB runs code
- actions/etl-aifirst/scripts/fit.py 7.2 KB runs code
- actions/etl-aifirst/scripts/gate_a.py 194 KB runs code
- actions/etl-aifirst/scripts/gate_b.py 95 KB runs code
- actions/etl-aifirst/scripts/identify.py 98 KB runs code
- actions/etl-aifirst/scripts/integrity_gate.py 55 KB runs code
- actions/etl-aifirst/scripts/issue-inventory/proposals/AIM-REF-19ec51fddf7b.json 1.3 KB
- actions/etl-aifirst/scripts/issue-inventory/proposals/AIM-SEM-2854b30f4eb4.json 1.6 KB
- actions/etl-aifirst/scripts/issue-inventory/proposals/AIM-SEM-fea89cc30673.json 1.9 KB
- actions/etl-aifirst/scripts/issue-inventory/proposals/AIM-SHAPE-d11b10218611.json 1.5 KB
- actions/etl-aifirst/scripts/issue-inventory/types/AIM-EMIT-c585d372314d.json 4.6 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.
- 2d ago First seen · 181 lines · 0 tokens per session scan A ba3bc60b18b8
migrate-objects 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 45 tokens to every session and 3,213 once invoked, about $0.0002 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.