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 keithbinkly/dbt-meta-context --skill authoring-meta-contextgit clone --depth 1 https://github.com/keithbinkly/dbt-meta-contextWrote 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/keithbinkly/dbt-meta-context/authoring-meta-context)<a href="https://agentmods.dev/skills/keithbinkly/dbt-meta-context/authoring-meta-context"><img src="https://agentmods.dev/badge/skills/keithbinkly/dbt-meta-context/authoring-meta-context.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.01063 |
| Opus 5 | $0.00048 | $0.00531 |
| Sonnet 5 | $0.00019 | $0.00213 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
authoring-meta-context 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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring Meta Context
Quick start
- Gather source docs (runbooks, wikis, SLA contracts, post-mortems) for your target metric.
- Run the distillation prompt against them: see guides/distillation-prompt.md.
- Paste the draft
meta:block into your semantic model YAML. - Validate:
dbt-mc validate path/to/semantic_model.yml - Fill
# NEEDS REVIEWand# NOT FOUNDgaps from the output.
Start with Bronze tier (13 Core fields, ~45 min/metric) on your 5–10 most-questioned metrics.
Authoring workflow
- Collect source docs (see guides/sourcing.md for field-by-field source map)
- Run distillation prompt — fills 60–70% of schema from existing docs
- Review output: verify
# NEEDS REVIEWitems; fill# NOT FOUNDgaps with the metric owner (see guides/interview.md for the domain-expert interview questions) - Add
business_rules(Layer 5) for any metric tied to a customer or regulatory SLA — absence creates false confidence - Validate with
dbt-mc validate— check for type errors and false-confidence risk - Set
last_validatedto today's date
The 5 layers
| Layer | Question | Failure it closes |
|---|---|---|
| 1. Context | Who cares and why does this exist? | Interpretation |
| 2. Expectations | What does good look like? | Calibration |
| 3. Investigation | When it breaks, where do I look? | Framing |
| 4. Relationships | What else moves when this moves? | Reasoning |
| 5. Decisions | What do I do about it? | Action + false confidence |
Critical: Layers 2–4 without Layer 5 create false confidence. An agent that knows healthy ranges but not business rules will give confidently wrong answers on SLA and compliance questions.
Authoring principles
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.
- 8d ago First seen · 73 lines · 97 tokens per session scan A 7e9c4e9b7cb1
authoring-meta-context is a skill published in the GitHub repository keithbinkly/dbt-meta-context (12 stars, last pushed 14d ago), licensed MIT. It adds 97 tokens to every session and 1,063 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
dbt-agent-readiness
Audit a dbt project for agent-readiness: what would an AI agent get wrong if you pointed it at this data today? Produces a prioritized report organized by failure modes (wrong numbers, wrong table, wrong column, can't join, query fails). Scales via two-pass architecture with parallel subagents. Each subagent reads its…
create-task
Scan a dbt project and generate ADE-Bench benchmark tasks. Analyzes models, proposes bug-injection scenarios by difficulty, and outputs complete task scaffolding (task.yaml, patches, setup/solution scripts, test SQL). Use when you want to benchmark AI agents against your own dbt project and data.
embed
Generate, inspect, and use node/text embeddings in Semantica — compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link…
visualize
Visualize the Semantica knowledge graph — topology, centrality, communities, paths, embeddings, decision insights, and temporal evolution. Uses GraphAnalyzer, CentralityCalculator, CommunityDetector, PathFinder, and ContextGraph analytics. Sub-commands: topology, centrality, community, path, decision-graph, insights…
reason
Run reasoning over the Semantica knowledge graph — deductive logic, abductive hypothesis generation, Datalog programs, SPARQL queries, Rete network evaluation. Uses DeductiveReasoner, AbductiveReasoner, DatalogReasoner, SPARQLReasoner, ReteEngine. Sub-commands: deductive, abductive, datalog, sparql, rete, prove…
temporal
Temporal graph operations on Semantica — scoped queries at a point in time, graph snapshots, node change timelines, temporal causal analysis, and graph state reconstruction. Uses AgentContext.findprecedents(asof=), ContextGraph.stateat(), CausalChainAnalyzer.traceattime(), and TemporalQueryRewriter. Sub-commands…