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.
npx skills add Cratis/AI --skill cratis-arc-command-operationgit clone --depth 1 https://github.com/Cratis/AIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cratis/ai/cratis-arc-command-operation)<a href="https://agentmods.dev/skills/cratis/ai/cratis-arc-command-operation"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-arc-command-operation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cratis/ai/cratis-arc-command-operation"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-arc-command-operation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00083 | $0.03294 |
| Opus 5.5 | $0.00033 | $0.01318 |
| Sonnet 5.5 | $0.00017 | $0.00659 |
| Haiku 4.5 | $0.00008 | $0.00329 |
Grade A, and why
cratis-arc-command-operation 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Return work from an Arc command
A command should be able to decide which seat to reserve without reserving it
in the decision spec. Handle() returns immutable descriptions of the work;
Arc executes them and, when the commit boundary permits, compensates attempted
work. You write the business reversal, not a rollback stack.
Command operations are the recommended way to express immediate inline side effects in model-bound commands. Direct service calls remain supported. Chronicle is not required.
Verified product sources
| Package / source assembly | Purpose |
|---|---|
Cratis.Arc.Core |
Cratis.Arc.Commands: operation declarations, pipeline, scopes, recovery observations |
Cratis.Arc.Core.CodeAnalysis / Cratis.Arc.Core.Generators |
ARC0016–ARC0018 and typed invocation; generator ships inside Core, not as a standalone package |
Cratis.Arc.ProxyGenerator |
Excludes operations and batches from the client response |
Cratis.Arc.Testing |
Cratis.Arc.Testing.Commands.CommandScenario<TCommand> and operation assertions |
Cratis.Arc.Chronicle / Cratis.Arc.Chronicle.Testing |
Deferred event commitment and real in-process constraint-rejection specs |
Sources:
Operation docs,
execution reference,
Source/DotNET/Arc.Core/Commands/, the analyzer/generator, and the testing
sources. These are C# APIs, not the separate
Arc for TypeScript server API.
Choose the boundary
| Need | Use |
|---|---|
| Acquire data for the decision | Provide() or explicitly supplied decision inputs |
| Reject input or a business decision | Validators or a recognized ValidationResult alternative |
| Return information | An ordinary response |
| Perform immediate external work chosen by the command | ICommandOperation |
| Reverse attempted work after an eligible failure | Optional Compensate() |
| Record durable Chronicle facts | Returned events, enrolled for deferred commitment |
| Reliable work after commit: email, payments, retriable webhooks | A reactor, outbox, or durable workflow; not inline operations |
| Use an external result to make the decision or response | An explicit service call; operations cannot return receipts |
| Extend framework interpretation of a specialized return type | Response value handlers, not application operation orchestration |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · -1 lines 1cf47ac31dc5
- 9d ago Changed · +1 lines 8a6960d94181
- 12d ago Changed · +4 lines 0210832c0649
- 19d ago First seen · 278 lines · 83 tokens per session scan A 0c9fc85e8382
cratis-arc-command-operation is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 3,294 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
Event Sourcing Testing
Testing event sourcing patterns including event store validation, projection testing, saga orchestration, and event versioning compatibility.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…