domain

A set of instructions for understanding Codex Studio before exploring or changing it. It points to the product glossary, architecture description, accepted design decisions, and workflow guide.

In plain words
What is it for?
Use it before modifying Codex Studio to find the correct product vocabulary, understand the system structure, check relevant architecture decisions, and follow the documented provider, recipe, preset, output, storage, and setup workflows.
Why use it?
It reduces the risk of using inconsistent terms or making changes that conflict with decisions the project has already accepted. Missing terms are recorded for focused review instead of being silently added during unrelated work.

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/gvastethecreator/codex-studio/domain
Clone the repo
git clone --depth 1 https://github.com/gvastethecreator/codex-studio
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 221 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 $0.00221
Opus 5 $0.00000 $0.00111
Sonnet 5 $0.00000 $0.00044
Haiku 4.5 $0.00000 $0.00022

Measured 2d ago against content hash 9d04a2d60f3c, 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 · 28 lines

What it actually says

Domain docs

Read these documents before you explore or change Codex Studio:

  • Read CONTEXT.md for canonical product terms.
  • Read docs/ARCHITECTURE.md for the current system shape.
  • Read the relevant files under docs/adr/ for accepted decisions.
  • Read SKILLS.md for provider, recipe, preset, output, storage, and setup workflows.

Layout

Codex Studio uses one domain context:

/
├── CONTEXT.md
├── docs/
│   ├── ARCHITECTURE.md
│   └── adr/
└── SKILLS.md

Use the terms from CONTEXT.md in Issues, plans, tests, and implementation notes. Do not replace a canonical term with a synonym that the glossary rejects.

If a proposal conflicts with an ADR, name the ADR and the conflict. Do not replace the accepted decision in silence.

If a needed term is missing, record the gap for a focused domain review. Do not expand CONTEXT.md during unrelated work.

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 · 28 lines · 0 tokens per session scan A 9d04a2d60f3c

Subscribe to this mod's changes

domain is an agent published in the GitHub repository gvastethecreator/codex-studio (12 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 221 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 2026-08-30.

Related

Other agents, from other repositories