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 agentmods add skills/cratis/ai/call-command-from-codenpx skills add Cratis/AI --skill call-command-from-codegit clone --depth 1 https://github.com/Cratis/AIWhat 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 | $0.00066 | $0.00954 |
| Opus 5 | $0.00033 | $0.00477 |
| Sonnet 5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00095 |
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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- call-command-from-code — 100% identical, 0 lines differ
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 injectIEventLog— returnIEnumerable<object>withEventForEventSourceId(targetId, @event)wrappers (seevertical-slices.md).ICommandPipelineis 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).
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.
- yesterday First seen · 82 lines · 66 tokens per session scan A 4fb567fb9b9c
call-command-from-code is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 954 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ship-changes
Ship staged or unstaged local changes: create a branch, make logical commits, push to origin, open a PR with the correct description and label, merge it, close the issues it resolves, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or land changes.
add-concept
Use this skill when asked to create a strongly-typed domain identifier or value (such as ProjectId, AuthorName, InvoiceNumber) in a Cratis-based project. Produces a ConceptAs record with the correct conversions and sentinel values.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
cratis-command
Step-by-step guidance for creating a Cratis Arc command — [Command] record, Handle() method, CommandValidator, proxy generation, and React .use() hook with CommandDialog. Use when adding or creating a command, wiring up a form or button to the backend, working with IEventLog, CommandResult, CommandValidator…
cratis-readmodel
Step-by-step guidance for creating a Cratis Chronicle read model from scratch — defining events, choosing between projection and reducer, [ReadModel] record with static query methods, and the generated TypeScript proxy in React. Use when creating a read model, working with [EventType], [ReadModel], IProjectionFor…
auth-and-identity
Use this skill for authentication, authorization, or identity in a Cratis Arc project — backend, frontend, or both. Covers identity providers (IProvideIdentityDetails), protecting commands/queries with authorization attributes, Microsoft Identity Platform, connecting backend identity to React, multi-tenant identity…