domain

Repository-specific instructions for using domain documentation, such as context files, architectural decisions, strategy, concepts, and recorded solutions, when exploring code.

In plain words
What is it for?
Use them when exploring or changing a repository so relevant documentation is read before working in an area.
Why use it?
They reduce confusion about project vocabulary and help keep code exploration aligned with documented design decisions.

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/spiritledsoftware/caplets/domain
Clone the repo
git clone --depth 1 https://github.com/spiritledsoftware/caplets
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 382 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 $0.00382
Opus 5 $0.00000 $0.00191
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured yesterday against content hash d6df4d055ee3, 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 · 34 lines

What it actually says

Domain Docs

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

Layout

This is a single-context repo.

  • Read root CONTEXT.md for Caplets product vocabulary and domain language.
  • Read relevant ADRs in docs/adr/ before changing areas covered by an architectural decision.
  • If a future CONTEXT-MAP.md appears, treat that as a signal that the repo has moved to a multi-context layout and update this file.

Before exploring, read these

  • CONTEXT.md at the repo root.
  • docs/adr/ entries that touch the area you're about to work in.
  • STRATEGY.md when deciding whether proposed work fits the current product direction.
  • CONCEPTS.md when orienting to shared project vocabulary.
  • docs/solutions/ when implementing, debugging, or making decisions in an area with documented prior solutions.

If any optional file does not exist in a checkout, proceed silently. Do not suggest creating it upfront; producer workflows create or update these docs when terms, strategy, or decisions are actually resolved.

Use the glossary's vocabulary

When your output names a domain concept in an issue title, refactor proposal, hypothesis, test name, or implementation plan, use the terms defined in CONTEXT.md and CONCEPTS.md. Do not drift to synonyms those docs explicitly avoid.

If the concept you need is not in the glossary yet, either reconsider whether you are inventing language the project does not use, or note the gap for a vocabulary/documentation pass.

Flag ADR conflicts

If your output contradicts an existing ADR, surface it explicitly rather than silently overriding:

Contradicts ADR-0001 (Code Mode default exposure), 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. yesterday First seen · 34 lines · 0 tokens per session scan A d6df4d055ee3

Subscribe to this mod's changes

domain is an agent published in the GitHub repository spiritledsoftware/caplets (14 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 382 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.