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/add-reactornpx skills add Cratis/AI --skill add-reactorgit 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/add-reactor)<a href="https://agentmods.dev/skills/cratis/ai/add-reactor"><img src="https://agentmods.dev/badge/skills/cratis/ai/add-reactor.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01521 |
| Opus 5 | $0.00017 | $0.00760 |
| Sonnet 5 | $0.00007 | $0.00304 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
add-reactor 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 today.
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:
- add-reactor — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a Chronicle reactor that triggers automation or translation logic in response to events.
Always read the reactors.md rule first. It is the source of truth for reactor conventions, rules, and patterns.
Step 1 — Identify the event(s)
Determine which event type(s) the reactor needs to observe. These events must already exist or be created as part of the slice.
Step 2 — Create the reactor class
Place the reactor in the appropriate feature folder, co-located with the slice it belongs to.
// Copyright (c) Cratis. All rights reserved.
// Licensed under the MIT license. See LICENSE file in the project root for full license information.
namespace MyApp.Projects.Notifications;
/// <summary>
/// Sends a notification when a project is registered.
/// </summary>
/// <param name="notifications">The notification service.</param>
public class ProjectRegisteredNotifier(INotificationService notifications) : IReactor
{
/// <summary>
/// Reacts to <see cref="Registration.ProjectRegistered"/> events.
/// </summary>
/// <param name="event">The event.</param>
/// <param name="context">The event context.</param>
public async Task ProjectRegistered(Registration.ProjectRegistered @event, EventContext context) =>
await notifications.Notify($"Project '{@event.Name}' was registered.");
}
Step 3 — Follow the critical rules
IReactoris a marker interface — no methods to implement. Method dispatch is by first-parameter event type.- Method name — can be anything descriptive. The name is for readability, not dispatch.
EventContext— optional second parameter. Omit if event metadata is not needed.- Idempotent — reactors may be called more than once for the same event. Design accordingly.
- Use event data directly — never query the read model back inside the reactor.
- Return events instead of injecting IEventLog — to produce new events, return them directly as
Task<TEvent>,Task<EventForEventSourceId>, or a collection thereof. For commands in other slices, injectICommandPipeline. Avoid injectingIEventLogdirectly.
What ships with it
1 file 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.
- today Changed 4d097e7cb9d7
- 3d ago First seen · 150 lines · 35 tokens per session scan A a0067468efcf
add-reactor is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,521 once invoked, about $0.0002 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
add-reactor
Use this skill when asked to add a Chronicle reactor (automation or translation) to a Cratis-based project. Reactors observe events and produce side effects.
cratis-vertical-slice
Explains how vertical feature slices are structured in a Cratis Chronicle + Arc application — folder layout, the single backend .cs file, the four slice types (State Change/View/Automation/Translation), and how features compose slices. Use when asking how slices work, where files go, or which slice type to choose. To…
create-event-model
Create and maintain Mermaid eventmodeling diagrams (EventModel.md) for a Cratis module or feature. Use when adding, renaming, moving, or deleting modules/features/slices, commands, events, read models, automations, translations, or cross-module event flows — to keep the diagram in sync with the code.
event-modeling
Design a Cratis event model before writing code — decide stream boundaries, commands, events, read models, automations/translations, compliance subjects, and the spec outline. Use this when behavior, event vocabulary, stream boundaries, or a multi-slice flow is not yet settled, before implementing a slice.
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.