domain

A repository-specific instruction that tells an agent to read the root CONTEXT.md file before changing behavior. It keeps the project’s terminology and documented decisions consistent in code, tests, issues, and public documentation.

In plain words
What is it for?
Use it in a repository where CONTEXT.md is the source for domain language and working assumptions, especially before modifying behavior or writing related documentation.
Why use it?
It prevents changes based on guessed meanings or conflicting vocabulary. It also directs the agent to review architecture records and note concepts that the project has not defined.

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/mheraskin/soloe/domain
Clone the repo
git clone --depth 1 https://github.com/mheraskin/soloe
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 78 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 $0.00078
Opus 5 $0.00000 $0.00039
Sonnet 5 $0.00000 $0.00016
Haiku 4.5 $0.00000 $0.00008

Measured yesterday against content hash 5c6cc76b0328, 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 yesterday.

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 · 8 lines

What it actually says

Domain docs

This is a single-context repository. Read the root CONTEXT.md before changing behavior and use its terms in tests, code, issues, and public documentation.

Read relevant records under docs/adr/ when that directory exists. If a needed concept is absent from the glossary, avoid inventing a synonym and record the terminology gap for later discussion.

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. yesterday First seen · 8 lines · 0 tokens per session scan A 5c6cc76b0328

Subscribe to this mod's changes

domain is an agent published in the GitHub repository mheraskin/soloe (1 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 78 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.

Related

Other agents, from other repositories

executor

The main task execution agent. Spawned for each task in a project. Executes the task described in its prompt — builds, tests, commits, and verifies. Use this when a project task needs to be executed autonomously.

yuchenbigpen1/normies · 47 tokens

integration-checker

Runs once at the end of a project, after all steps complete. Verifies that all pieces connect correctly across step boundaries — exports used, APIs called, data flows end-to-end. Returns a comprehensive integration report.

yuchenbigpen1/normies · 47 tokens

verifier

Runs between steps to independently verify the previous step's work. Uses goal-backward verification: checks that the step achieved its GOAL, not just that tasks completed. Three-level artifact verification (exists, substantive, wired). Returns pass/fail verdict with evidence.

yuchenbigpen1/normies · 55 tokens

spot-checker

Lightweight check that runs between waves. Quickly verifies that files from the completed wave exist and commits are real. Fast gate — not a full review. Uses haiku for speed and cost.

yuchenbigpen1/normies · 42 tokens

apm-primitives-architect

Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…

microsoft/apm · 74 tokens

detection-matrix

Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.

sstraus/tuicommander · 0 tokens