A set of instructions for how engineering skills should use this repository’s domain documentation. It points agents to project context, architecture decisions, specifications, and operating rules before they explore or change code.

Use it when exploring or implementing work in this repository, especially in areas covered by its context files, architecture records, ACRYL or Cordis documentation, and project constitution.

It helps an agent understand the project’s own terms and constraints instead of treating unfamiliar code as generic software. That reduces the chance of making changes that conflict with documented decisions.

domain — Agent by acryldev

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/acryldev/acryl/domain

Clone the repo

git clone --depth 1 https://github.com/acryldev/acryl

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 492 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00492
Opus 5	$0.00000	$0.00246
Sonnet 5	$0.00000	$0.00098
Haiku 4.5	$0.00000	$0.00049

Measured 2d ago against content hash 8340aba23f58, 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 · 56 lines

What it actually says

Domain Docs

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

Before exploring, read these

CONTEXT.md at the repo root, if it exists.
docs/adr/ — ADRs that touch the area you are about to work in.
.specify/memory/constitution.md — binding ACRYL/Cordis laws.
docs/onboarding/orientation_spec_acryl.md — product mission.
docs/cordis/cordis_spec.md — Cordis runtime onboarding.
docs/cordis/cordis_system_guide_for_coding_agents.md — operational Context, Fiber, service, injection, effect, event, Tool, Loader, and HMR rules.
docs/cordis/acryl_cordis_alignment_audit.md — current project compliance, transitional debt, and pre-implementation gates.
docs/acryl/ — gap analysis, concept, roadmap, decisions as they appear.

If CONTEXT.md or docs/adr/ do not exist, proceed silently. The /domain-modeling skill creates them lazily when terms or decisions actually get resolved.

File structure

Single-context repo:

/
├── CONTEXT.md                 ← created lazily by domain-modeling
├── docs/adr/                  ← created lazily
├── docs/acryl/                  ← ACRYL architecture artifacts
├── docs/cordis/
├── docs/onboarding/
├── specs/                     ← Spec Kit + Wayfinder
└── acryl-desktop/

Use the glossary's vocabulary

Prefer terms already defined in the orientation spec, Cordis spec, and constitution:

plugin, context, service, provider, consumer, inject, effect, fiber
room, relay, handoff, projection, generation
HOT / WARM / COLD
DSH-native agent, PTY agent, ACP agent
capability package

Do not drift to synonyms the constitution avoids (for example "rewrite the harness", "agent-owned project", "mega prompt format").

Flag ADR conflicts

If output contradicts an existing ADR or the constitution, surface it explicitly rather than silently overriding.

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.

2d ago First seen · 56 lines · 0 tokens per session scan A 8340aba23f58

Subscribe to this mod's changes

domain is an agent published in the GitHub repository acryldev/acryl (220 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 492 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.

Building agents acryl agent-context-relay agentic-development-environment ai-agents cordis deepseek-harness

domain

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Domain Docs

Before exploring, read these

File structure

Use the glossary's vocabulary

Flag ADR conflicts

What this file has done since we first saw it

Other agents, from other repositories

orchestrator

ds-flash

ds-pro

analyzer

grader

comparator