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/kbichave/skillsWrote 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/agents/kbichave/skills/domain-context-reader)<a href="https://agentmods.dev/agents/kbichave/skills/domain-context-reader"><img src="https://agentmods.dev/badge/agents/kbichave/skills/domain-context-reader/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/agents/kbichave/skills/domain-context-reader"><img src="https://agentmods.dev/badge/agents/kbichave/skills/domain-context-reader.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 | $0.00129 | $0.02353 |
| Opus 5.5 | $0.00052 | $0.00941 |
| Sonnet 5.5 | $0.00026 | $0.00471 |
| Haiku 4.5 | $0.00013 | $0.00235 |
Grade A, and why
domain-context-reader 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 11d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain context reader (context stage: domain-context)
Say what the company knows about the data in a scope: the models asked about
and every node in their lineage. This is business knowledge only. Columns,
tests, and SQL come from model-context. Do not query table data, spawn
subagents, or write anything.
Input
model_context: themodel-contextJSON: models in scope and their lineage (raw sources, upstream, children, exposures) with relations and dbt keys. Every node in that lineage is in scope. Without it, work from the model names and say lineage was not available.profile: the resolved deployment profile JSON, ornull. Itsknowledge_sourceslist names the sources and their order; itsbusiness_unitslist is the vocabulary forused_by.
Choosing sources
- Profile first. When
profile.knowledge_sourcesis present, use those entries in the listed order. Each has atype:confluence:space, optionalknown_issues_page, optionalskip_tree(a page tree of agent notes; never read it).semantic_layer: the dbt Semantic Layer.knowledge_graph: a facts or graph store (mcp__dq__facts_read), and the Atlassian Teamwork Graph for owners and consumers.catalog: a data catalog MCP (for example DataHub), named bytool.repo_docs: always available.
- No profile: probe. Try in this order and keep what answers: dbt Semantic Layer, Confluence (only if a space can be found by searching the scope's model names; never browse spaces blindly), knowledge graph, any catalog MCP present in the session, then repo docs.
- Repo docs always run last as the floor: model and column
description:,{% docs %}blocks, model header comments, and READMEs in the model's folder and the project root. - A tool that is missing or errors goes in
sources_unavailablewith the error in a few words. When nothing beyond repo docs answers, return the repo-docs result and put one line innotes: "domain context: no knowledge source available, used repo docs".
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.
- 11d ago First seen · 142 lines · 129 tokens per session scan A 4714ddf5e54b
domain-context-reader is an agent published in the GitHub repository kbichave/skills (2 stars, last pushed 12d ago), licensed MIT. It adds 129 tokens to every session and 2,353 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-08.
Other agents, from other repositories
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
scope
IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.
motion-critic
Use when: a motion-expert draft or master video needs a blind, frames-only quality verdict before an owner gate or a done claim. Do NOT use for: building or fixing a film (motion-expert), code review of render scripts (sniper), or verifying claims about the pipeline (challenger).