domain

A reference guide explaining how engineering skills should use a repository’s domain documentation. It identifies files such as SKILL.md, gotchas.md, context notes, and architecture decision records as sources of project-specific truth.

In plain words
What is it for?
Use it when working on this repository’s modules, routing, or analysis claims. It tells the agent which documentation to read before proposing changes and where lasting architectural decisions belong.
Why use it?
It prevents agents from making assumptions about the project’s terminology, structure, or design decisions. It also clarifies that this repository is maintained through Markdown files rather than a software build system.

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/mrbinnacle/azimuth/domain
Clone the repo
git clone --depth 1 https://github.com/MrBinnacle/azimuth
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 319 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 $0.00319
Opus 5 $0.00000 $0.00160
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 2d ago against content hash 513f81d0fe2d, 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 · 24 lines

What it actually says

Domain Docs

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

Layout

Single-context repo. If CONTEXT.md and docs/adr/ exist at the repo root, read them before exploring. If they don't exist yet, proceed silently — they are created lazily as terms and decisions are resolved.

Repo context summary

AZIMUTH is a pure-markdown AI agent skill for decision quality analysis. There is no build system, no runtime, no tests. All "development" is editing .md files. Key domain vocabulary lives in SKILL.md (the skill entry point) and gotchas.md.

Before working on module logic, routing, or analysis claims, check SKILL.md and gotchas.md directly — they are the authoritative source of domain truth for this repo.

ADRs

docs/adr/ is the durable record of architectural decisions going forward. Read it before proposing structural changes. ADR-0001 records the bespoke maintenance orchestration layer; future ADRs are created lazily by /grill-with-docs when a real decision is resolved.

CHANGELOG.md remains the record for shipped behavioural changes (versioned releases); ADRs cover meta-design decisions about how the repo itself is structured and maintained.

Flag ADR conflicts

If your output contradicts an existing ADR in docs/adr/, surface it explicitly rather than silently overriding. Quote the ADR and explain why it should be reopened. Also check CHANGELOG.md for prior behavioural decisions that may bear on the change.

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 · 24 lines · 0 tokens per session scan A 513f81d0fe2d

Subscribe to this mod's changes

domain is an agent published in the GitHub repository MrBinnacle/azimuth (8 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 319 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.