A development workflow that combines Allium behavior specifications with Event Model service-topology work for Grain projects. A service topology describes how services, events, and system parts fit together.

Use it for Grain feature work, specifications, implementations, reconciliation, behavioral tests, topology validation, and composition checks.

It provides a defined loop for gathering requirements, writing behavioral and topology tests, implementing changes, and checking the result. It also catches mismatches between intended behavior and the running system.

grain — Skill by ObneyAI

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 skills/obneyai/grain/grain

Any agent

npx skills add ObneyAI/grain --skill grain

Clone the repo

git clone --depth 1 https://github.com/ObneyAI/grain

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 429 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	$0.00072	$0.00429
Opus 5	$0.00036	$0.00215
Sonnet 5	$0.00014	$0.00086
Haiku 4.5	$0.00007	$0.00043

Measured 2d ago against content hash 4a680d260321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grain 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.

skills/grain/SKILL.md · 39 lines

What it actually says

Grain

Use Allium as the behavioural host and Event Model as its Grain topology extension. Never copy behavioural rules or Given/When/Then into Event Model.

Preflight

Confirm the Allium entry and verb skills are installed. If not, pause and give the installation command appropriate to the active editor from https://github.com/juxt/allium. Do not vendor or silently replace Allium.

Inspect .allium files, defeventmodel forms, the live Grain catalog when available, and current tests. Decide whether the goal changes behaviour, topology, or both.

Composed loop

Gather durable context with Allium elicit or distill, then run the matching event-model-elicit or event-model-distill phase for topology.
Use Allium propagate for behavioural tests. Use event-model-propagate for topology, boot-mandate, and composition contract tests.
Implement and run tests. Confirm new behavioural tests were red before the implementation when doing spec-first work.
Verify with Allium weed, allium check, and allium analyse; then run event-model-weed, strict runtime validation, and composition validation.
If behaviour was wrong, revise with Allium tend; if topology was wrong, use event-model-tend. Re-propagate and repeat.

Finish only when behavioural specs, topology, generated tests, implementation, runtime registries, and Allium trace links agree and no open question remains.

Read the event-model skill for the Grain schema and exact REPL APIs.

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 · 39 lines · 72 tokens per session scan A 4a680d260321

Subscribe to this mod's changes

grain is a skill published in the GitHub repository ObneyAI/grain (118 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 429 once invoked, about $0.0004 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 2026-08-30.

Data and AI Productivity Testing agents clojure eventsourcing

agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer.

ruvnet/ruflo · 19 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens