domain

A guide for reading a software repository’s domain documentation before exploring or changing its code. Domain documentation explains the project’s own terms, structure, and important design decisions.

In plain words
What is it for?
It is for preparing engineering work by reading `AGENTS.md`, `CONTEXT.md`, and relevant architecture decision records, then using the glossary’s terms in tickets, hypotheses, refactors, and tests.
Why use it?
It helps the agent use the project’s established vocabulary and follow its documented constraints. It also directs the agent to check repository rules, context notes, and architecture decisions first.

Agent

Install

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.

agentmods
npx agentmods add agents/darecstowell/scratchboard/domain
Clone the repo
git clone --depth 1 https://github.com/darecstowell/scratchboard
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00380
Opus 5 $0.00000 $0.00190
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured 2d ago against content hash 686e65a22321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

domain 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.

docs/agents/domain.md · 46 lines

What it actually says

Domain docs

How the engineering skills read this repo's domain documentation before they explore the code.

Before exploring, read these

  • CONTEXT.md at the repo root.
  • docs/adr/ for the decisions that touch the area you are about to work in.

If a file does not exist, continue silently. Do not report that it is missing, and do not propose to create it up front. The /domain-modeling skill, reached through /grill-with-docs and /improve-codebase-architecture, writes these files when a term or a decision is actually resolved.

AGENTS.md holds the rules of this repo and is not a domain doc, but read it first. It states the constraints that a change must keep.

File structure

This repo is single-context:

/
├── AGENTS.md
├── CONTEXT.md
├── docs/adr/
│   ├── 0001-zero-dependencies.md
│   └── 0002-config-names-every-lane.md
└── src/

Use the glossary's vocabulary

When your output names a domain concept, in a ticket title, a refactor proposal, a hypothesis, or a test name, use the term as CONTEXT.md defines it. Do not drift to a synonym the glossary avoids.

If the concept is not in the glossary, that is a signal. Either you invent language the project does not use, so think again, or there is a real gap, so note it for /domain-modeling.

Flag ADR conflicts

If your output contradicts an ADR, say so instead of overriding it quietly:

Contradicts ADR-0001 (zero dependencies), but worth reopening because...

Changes

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.

  1. 2d ago First seen · 46 lines · 0 tokens per session scan A 686e65a22321

Subscribe to this mod's changes

domain is an agent published in the GitHub repository darecstowell/scratchboard (6 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 380 tokens. 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 2026-08-31.