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 OutlineDriven/odin-claude-plugin --skill dbt-model-indexgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/dbt-model-index)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/dbt-model-index"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/dbt-model-index/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/outlinedriven/odin-claude-plugin/dbt-model-index"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/dbt-model-index.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 | $0.00035 | $0.00865 |
| Opus 5 | $0.00017 | $0.00432 |
| Sonnet 5 | $0.00007 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
dbt-model-index 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 4d 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.
This is a copy
100% identical to dbt-model-index — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt model index
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user needs to query data in a dbt-powered data warehouse or resolve a data question. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Consults the curated model index and emits SQL without executing it. |
| Side effect | Produces a BigQuery SQL query that references the correct model; no warehouse mutation |
| Done | Query uses the correct fully-qualified model name, respects documented standard filters, partition fields, grain, and cost controls |
Inputs
- A data question or query intent (required). May be vague or ambiguous.
- The human-curated model index in the Curated Model Index section (required). The human maintains one entry per dbt model, organized by domain. Each entry must record: fully-qualified table reference, grain (one row per what), useful-for query patterns, join keys, standard filters, and partition fields.
- Standard filters, production dataset path, plan or tier valid values, and sensitive-dataset callouts documented in the Curated Model Index section (required when the project has them).
Procedure
- Read the data question. If it names specific models, skip to step 4. Done when: the data question is read and the path (model-named or index-scan) is determined.
- Scan the Curated Model Index section. Match the question to the model whose grain and useful-for patterns best fit the intent. Done when: the best-fit model is identified from the index.
- If no single model fits, identify the join keys that connect candidate models and note each model's grain to avoid fan-out. Done when: join keys are identified and grains noted, or a single model is selected.
- Construct the fully-qualified table reference using the production dataset path documented in the Curated Model Index section. For sensitive datasets, use the separate dataset path called out there. Done when: the fully-qualified table reference uses the correct dataset path.
- Apply every standard filter documented in the Curated Model Index section (for example, excluding test accounts, soft-deleted records, internal users, flagged or fraudulent users). Omit none. Done when: every documented standard filter is applied.
- For partitioned tables, filter on the partition field and constrain the date range. Never issue an unbounded scan of a large partitioned table. Done when: partitioned tables are filtered on the partition field with a bounded date range.
- Include a comment stating the model grain (one row per what) so join cardinality is explicit. Done when: the query includes a grain comment.
- If the query references plan or tier types, filter only on the valid values documented in the Curated Model Index section. Done when: plan or tier filters use only documented valid values.
- Emit the BigQuery SQL query. Done when: the BigQuery SQL query is emitted with correct model name, all standard filters, partition constraints, grain comment, and valid-value filters.
What ships with it
1 file 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.
- 4d ago Changed · -22 tokens per session b3754cae9edb
- 6d ago First seen · 43 lines · 57 tokens per session scan A 66e28457f137
dbt-model-index is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 865 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to dbt-model-index, differing in 0 lines, and is treated as a copy.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…