add-reducer

A guide for adding a C# reducer, a component that combines the current read-model state with an event to produce the next state. It is intended for cases that simpler projection rules cannot express.

In plain words
What is it for?
Implementing read models that require branching, loops, or accumulated calculations unavailable through the supported declarative projection features.
Why use it?
It helps developers avoid using custom code when a simpler projection is sufficient and explains when custom state transitions are justified.

Skill for Claude CodeCodex

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/cratis/ai/add-reducer
Any agent
npx skills add Cratis/AI --skill add-reducer
Clone the repo
git clone --depth 1 https://github.com/Cratis/AI

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,030 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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.01030
Opus 5 $0.00035 $0.00515
Sonnet 5 $0.00014 $0.00206
Haiku 4.5 $0.00007 $0.00103

Measured 2d ago against content hash 7b789a34cad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-reducer 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.ai/skills/add-reducer/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding a Reducer (IReducerFor<T>)

A reducer is the last-resort way to build a read model — "current state + event → next state" with real C# control flow. Reach for it only when the projection ladder can't express the shape. A reducer that could have been a projection is a projection that was never written, and will be flagged for conversion in review.

Admission checklist — all three must be true before writing a reducer

  1. Model-bound attributes can't express it — not [FromEvent<T>], [SetFrom<T>], [SetFromContext<T>], [ChildrenFrom<T>], [RemovedWith<T>], [Nested], [ClearWith<T>], counters ([Increment<T>]/[Count<T>]), or [FromAll].
  2. Fluent IProjectionFor<T> can't express it — not UsingKey/UsingParentKey/UsingCompositeKey/UsingConstantKey, Join, .NotRewindable(), or a supported conditional setter.
  3. The remainder needs real control flow — branching on prior state, loops, or accumulated-state calculations the declarative APIs don't have.

If all three hold, write the reducer and carry an inline justification comment on the class naming the specific limitation that ruled out a projection:

// Reducer required: next balance depends on prior balance with a per-event cap that
// no counter/projection attribute expresses.
public class AccountBalanceReducer : IReducerFor<AccountBalance>
{
    public AccountBalance Opened(DebitAccountOpened @event, AccountBalance? current, EventContext context)
        => new(0m, context.Occurred);

    public AccountBalance Deposited(FundsDeposited @event, AccountBalance? current, EventContext context)
        => (current ?? new(0m, context.Occurred)) with { Balance = (current?.Balance ?? 0m) + @event.Amount };
}

Method signatures

Each public method's first parameter is the event type it handles (dispatch is by type, not name):

Signature Meaning
T On(TEvent @event, T? current) next state from current (null on first event)
T On(TEvent @event, T current) non-nullable current when the model is always seeded first
+ EventContext context add the context as a trailing parameter when you need Occurred/metadata
Task<T> On(...) async when the computation awaits
return T?/null treat the event as a no-op for this model

Read the full file on GitHub · 62 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. 2d ago First seen · 62 lines · 70 tokens per session scan A 7b789a34cad9

Subscribe to this mod's changes

add-reducer is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 1,030 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.

Related

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.

Cratis/VerticalSlices · 72 tokens

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.

Cratis/VerticalSlices · 54 tokens

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/VerticalSlices · 63 tokens

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/VerticalSlices · 80 tokens

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…

Cratis/VerticalSlices · 100 tokens

add-traces

Use this skill when asked to add OpenTelemetry tracing to a class in a Cratis Chronicle Kernel project. Produces Traces.cs companion files using the [Span] source-generator pattern from Cratis.Traces, registers IActivitySource as a keyed DI service, and injects it into the target class.

Cratis/VerticalSlices · 73 tokens