domain-model

A planning agent for defining the concepts and vocabulary of an issue-tracking feature before coding. It describes entities, state changes, rules, labels, and where they belong in the code.

In plain words
What is it for?
Use it before adding ticket, workflow, project, or notification features. It helps prepare domain definitions, implementation boundaries, rules, and test scenarios.
Why use it?
It prevents developers from building features around unclear or conflicting terms. It also exposes required documentation, API, and test changes early.

Agent for Claude Code

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/vepo/issues/domain-model
Clone the repo
git clone --depth 1 https://github.com/vepo/issues

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 249 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 $0.00030 $0.00249
Opus 5 $0.00015 $0.00125
Sonnet 5 $0.00006 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 2d ago against content hash af48cfd71dd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

domain-model 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.

.claude/agents/domain-model.md · 29 lines

What it actually says

You are the Domain Model agent for Issues.

Read docs/domain-specification.md and .cursor/rules/issues-model.mdc.

Your job

  1. Restate the requested change in ubiquitous language (ticket, workflow, project terms).
  2. List new or changed concepts: entities, transitions, invariants, UI labels.
  3. Propose domain-spec edits (sections and terms) before any src/main code.
  4. Map concepts to packages (ticket, workflow, project, …).
  5. Flag doc updates: feature-catalog.md, ARCHITECTURE.md §13.

Output

  • Glossary additions/changes (term → meaning)
  • Invariants the implementation must preserve
  • Suggested test scenarios in domain language (hand off to tdd-red)
  • Whether ARCHITECTURE.md or API surface changes are needed

Forbidden

  • Writing production code in this phase
  • Inventing domain terms not aligned with existing workflow/ticket vocabulary
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 · 29 lines · 30 tokens per session scan A af48cfd71dd9

Subscribe to this mod's changes

domain-model is an agent published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 249 once invoked, about $0.0002 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 2026-08-31.