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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/commands/kumaran-is/claude-code-onboarding/migrate-embedding-model)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/migrate-embedding-model"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/migrate-embedding-model.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.01042 |
| Opus 5 | $0.00030 | $0.00521 |
| Sonnet 5 | $0.00012 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
migrate-embedding-model 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 5d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate Embedding Model
Plan and generate a safe embedding model migration using expand-deploy-contract.
Input: $ARGUMENTS (e.g., "text-embedding-3-small text-embedding-3-large vendors tickets")
Steps
-
Load the
vector-databaseskill — readSKILL.mdandreferences/embedding-migration-guide.mdfor the full procedure. -
Gather requirements — Extract from
$ARGUMENTSor ask:- From model (current)
- To model (new)
- Tables/collections to migrate
- Migration format (Flyway SQL / Alembic Python / Weaviate Python)
-
Discover affected code — Grep the codebase for:
grep -rn "{from_model}" --include="*.py" --include="*.sql" --include="*.ts" grep -rn "embedding_model" --include="*.py" --include="*.sql"Report all files referencing the old model that will need updates.
-
Estimate cost:
- For each table:
SELECT COUNT(*), AVG(LENGTH({text_col})) FROM {table} - Calculate:
total_tokens = row_count × avg_chars / 4 - Cost at both model rates (from skill's model table)
- Report: "Estimated cost: $X.XX for {from_model} → {to_model}"
- For each table:
-
Generate migration artifacts:
Phase 1 — Expand migration (safe, reversible)
V{N}__expand_embedding_{table}_{new_model_slug}.sql- Adds
embedding_v2 vector({new_dims})column - Adds
embedding_model_v2 varchar(100)column - Creates HNSW index on
embedding_v2 - Adds
reembedding_status varchar(20) DEFAULT 'pending'
Re-embedding script
scripts/re_embed_{table}.py- Batch async re-embedding using
embed_batch() - Reads from
{text_col}, writes toembedding_v2 - Progress logging +
reembedding_statustracking - Idempotent:
WHERE embedding_v2 IS NULL - Dry-run mode:
--dry-runflag to preview without writing
Verification queries
scripts/verify_reembedding_{table}.sql- Count pending vs done
- Spot-check recall comparison (old vs new similarity scores)
- Adds
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.
- 5d ago First seen · 107 lines · 60 tokens per session scan A 318525c259b4
migrate-embedding-model is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,042 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 2026-09-03.
Other commands, from other repositories
laravel-vector-search
Add semantic/vector search with pgvector (Laravel 13+); use the laravel:vector-search skill exactly as written.
pgvector-search
Production hybrid search with PGVector and BM25 using Reciprocal Rank Fusion, metadata filtering, and performance tuning for semantic retrieval. Use when building hybrid semantic and keyword search, tuning PGVector performance, or filtering by metadata. Triggers on pgvector, hybrid search, BM25, reciprocal rank…
mindforge:embeddings
Design embedding and vector search system. Usage: /mindforge:embeddings [domain] [--db pinecone|weaviate|qdrant|pgvector] [--hybrid true|false].
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
db
Set up or operate Supabase Postgres for this project.
splunk-observability-database-monitoring-setup
Render and validate Splunk Observability Cloud Database Monitoring collector configuration for PostgreSQL, Microsoft SQL Server, and Oracle Database through the Splunk OTel Collector. Keeps secrets out of chat, argv, and rendered files; DB credentials are referenced through Kubernetes Secrets or local env vars.