VerticalSlices: Skill for Claude Code

.ai/skills/call-command-from-code/SKILL.md

call-command-from-code is a skill for Claude Code, Codex from Cratis/VerticalSlices. It costs 66 tokens per session (954 once invoked), scanned A, a copy of call-command-from-code, MIT.

Instructions for running a Cratis Arc backend command directly from application code through its command pipeline.

In plain words
What is it for?
Use it when backend code needs to trigger a command, either with a normal dependency-injection scope or with an existing scope.
Why use it?
It lets background jobs, event reactions, scheduled tasks, and tests use the same authorization and validation flow as an HTTP request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is Cratis/VerticalSlices's own configuration. It tells Claude Code and Codex how to work on VerticalSlices itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything VerticalSlices configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Cratis/VerticalSlices. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Cratis/VerticalSlices/main/.ai/skills/call-command-from-code/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Cratis/VerticalSlices

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for call-command-from-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/cratis/verticalslices/call-command-from-code/github.svg)](https://agentmods.dev/skills/cratis/verticalslices/call-command-from-code)
Your own site
<a href="https://agentmods.dev/skills/cratis/verticalslices/call-command-from-code"><img src="https://agentmods.dev/badge/skills/cratis/verticalslices/call-command-from-code/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.

agentmods 80×15 button for call-command-from-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/cratis/verticalslices/call-command-from-code"><img src="https://agentmods.dev/badge/skills/cratis/verticalslices/call-command-from-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 954 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00066 $0.00954
Opus 5.5 $0.00026 $0.00382
Sonnet 5.5 $0.00013 $0.00191
Haiku 4.5 $0.00007 $0.00095

Measured 1mo ago against content hash 4fb567fb9b9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

call-command-from-code 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 1mo 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.

Origin

This is a copy

100% identical to call-command-from-code — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.ai/skills/call-command-from-code/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Call a Command from Code

Backend code can drive a command through ICommandPipeline instead of an HTTP request. The pipeline runs the same authorization → validation → Provide() → Handle() chain as the HTTP boundary — only the entry point changes. Common callers: a reactor spawning a follow-up command, a background/scheduled job, an integration test harness.

Inside Handle() wanting to append to a different stream, do not inject IEventLog — return IEnumerable<object> with EventForEventSourceId(targetId, @event) wrappers (see vertical-slices.md). ICommandPipeline is for command-shaped invocations that need validation/authorization.

Steps

1. Inject and execute (scopeless overload)

public class <Source>Handler(ICommandPipeline pipeline) : IReactor
{
    [OnceOnly]
    public Task <Source>Created(<Source>Created @event, EventContext context) =>
        pipeline.Execute(new <TargetCommand>(@event.SourceId, @event.Name));
}

Execute(command) is the scopeless overload — the pipeline manages its own DI scope per call. This is the normal case.

2. Scoped overload — only when needed

Execute(command, serviceProvider) reuses the caller's ambient DI scope. Use it only when the handler genuinely depends on resolving something from that scope (e.g. a scoped DB session). Most callers don't need it.

3. Typed result

var result = await pipeline.Execute<RegistrationToken>(new Register(...));
if (result.IsSuccess) { var token = result.Response; }

4. Pre-flight Validate

await pipeline.Validate(command) runs authorization + validation without executing Provide()/Handle() — useful to confirm validity before committing to side effects. Scoped overload available.

Validation severity filtering: both Execute and Validate take an optional allowedSeverity of type ValidationResultSeverity? (from Cratis.Arc.Validation) — pipeline.Execute(command, allowedSeverity: ValidationResultSeverity.Warning). The levels are Unknown=0, Information=1, Warning=2, Error=3; by default only Error blocks, and failures at or below allowedSeverity are filtered out (so passing Warning lets warnings through but still blocks errors).

Read the full file on GitHub · 82 lines

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. 1mo ago First seen · 82 lines · 66 tokens per session scan A 4fb567fb9b9c

Subscribe to this mod's changes

call-command-from-code is a skill published in the GitHub repository Cratis/VerticalSlices (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 954 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to call-command-from-code, differing in 8 lines, and is treated as a copy.

Related

Other skills, from other repositories

cratis-screenplay-command-surface

Write the write side of a Cratis Screenplay .play model — the command block and its identifier, reads, validate, authorize, produces, handler and concurrency clauses, plus event, constraint, policy, persona, concept, type and seed. Use when declaring or changing a command, an event shape, a validation or authorization…

Cratis/AI · 126 tokens

cratis-screenplay-read-surface

Declare the read side of a Cratis Screenplay .play model — the readmodel shape, query with by/filter/scoped to/observable/performer, and screen at its three levels of detail, including the data/action contract that later component bindings, templates, forms, toolbars, routes and outlets consume. Use when adding or…

Cratis/AI · 146 tokens

cratis-arc-authentication-authorization-and-identity

Wire authentication, authorization and identity in a Cratis Arc application — IProvideIdentityDetails and the /.cratis/me endpoint, Arc's [Authorize]/[Roles]/[AllowAnonymous] attributes and named policies, fallback baselines, observable-query emission guards, IAuthenticationHandler, the Microsoft Identity Platform…

Cratis/AI · 129 tokens

cratis-arc-command-execution

Execute an existing Cratis Arc command from backend code through ICommandPipeline — the scopeless and scoped overloads, the typed generic Execute, the pre-flight Validate, validation severity filtering, and how to read CommandResult. Use when a reactor, background job, scheduled task, or backend service must run a…

Cratis/AI · 82 tokens

cratis-arc-command

Define a Cratis Arc command — the [Command] record, its Handle() method and return shape, the optional Provide() step, and the generated TypeScript proxy. Use when adding a command, choosing what Handle() should return, deciding which values may reach the causation chain (including API keys and other credentials…

Cratis/AI · 116 tokens

cratis-chronicle-client-dotnet

Talk to a Chronicle server from a standalone .NET application with the Cratis.Chronicle client - connection strings, ChronicleClient construction outside any host, AddCratisChronicle for a worker or ASP.NET host, [EventType] records, IEventSequence.Append, reactors and reducers found by assembly scanning, the…

Cratis/AI · 123 tokens