write-specs

A hook that runs before an AI agent receives a submitted prompt. It executes a JavaScript file from the surrounding plugin or project.

In plain words
What is it for?
Triggering prompt-related setup or processing through user-prompt-hook.js. The supplied information does not describe any more specific job.
Why use it?
It lets a project perform an automatic action whenever a prompt is submitted, before the agent processes it. The input does not say what that action does.

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/verticalslices/write-specs
Any agent
npx skills add Cratis/VerticalSlices --skill write-specs
Clone the repo
git clone --depth 1 https://github.com/Cratis/VerticalSlices

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00079 $0.01105
Opus 5 $0.00039 $0.00553
Sonnet 5 $0.00016 $0.00221
Haiku 4.5 $0.00008 $0.00111

Measured 2d ago against content hash e6bc79cd003e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-specs 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

This is a copy

100% identical to write-specs — 0 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/write-specs/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write comprehensive in-process BDD specs for an event-sourced Cratis application slice. Lead with the scenario family; reserve out-of-process Chronicle host specs for the host/transport boundary. Full patterns and assertion catalogs: .ai/rules/specs.scenarios.csharp.md (application profile).

Application-oriented. Most framework / library specs (Chronicle kernel, Arc pipeline, Fundamentals, generators) use the plain Specification base + NSubstitute — see specs.csharp.md. A framework repo reaches for the scenario family only to test the engine it provides (Arc's command pipeline, Chronicle's event/projection/reactor engine) — see specs.scenarios.csharp.md.

Spec placement

Specs live in the same slice folder as the .cs file, each file wrapped in #if DEBUG … #endif (spec code ships only in Debug):

<Feature>/<Slice>/
├── <Slice>.cs
└── when_<verb_phrase>/
    ├── and_<happy_scenario>.cs
    └── and_<failure_scenario>.cs

What to cover for every State Change command

One spec class for each of:

  1. Happy path — command succeeds, expected event appended (CommandScenario)
  2. Each validation failure — one and_ class per CommandValidator / ConceptValidator rule (CommandScenario)
  3. Each business rule violation — one and_ class per DCB condition in Handle() that inspects a read model (CommandScenario)
  4. Each constraint violation — one and_ class per IConstraint → use the write-specs-events skill (EventScenario)

Default: CommandScenario<TCommand> (in-process)

Runs authorization, validators, Provide(), and Handle() in-process and exposes the appended events — no HTTP, no fixture.

#if DEBUG
namespace MyApp.Projects.Registration.when_registering;

public class and_name_is_unique : Specification
{
    readonly CommandScenario<RegisterProject> _scenario = new();
    readonly ProjectId _id = ProjectId.New();
    CommandResult _result;

    async Task Because() => _result = await _scenario.Execute(new RegisterProject(_id, "My Project"));

    [Fact] void should_succeed() => _result.ShouldBeSuccessful();
    [Fact] async Task should_have_appended_the_registered_event() =>
        await _scenario.ShouldHaveAppendedEvent<RegisterProject, ProjectRegistered>(_id, e => e.Name == "My Project");
}
#endif

Read the full file on GitHub · 86 lines

Files

What ships with it

2 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.

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 · 86 lines · 79 tokens per session scan A e6bc79cd003e

Subscribe to this mod's changes

write-specs is a skill published in the GitHub repository Cratis/VerticalSlices (2 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 1,105 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to write-specs, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

write-specs

Use this skill to write specs for an event-sourced Cratis APPLICATION slice (command, query, projection, reactor, constraint) using the in-process scenario family (CommandScenario / EventScenario / ReadModelScenario / ReactorScenario); out-of-process Chronicle integration is an advanced fallback. NOT for…

Cratis/AI · 79 tokens

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, prepare no-effect dispositions for related issues, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or…

Cratis/AI · 74 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/AI · 80 tokens

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…

Cratis/AI · 88 tokens

cratis-react-page

Step-by-step guidance for building a React page in a Cratis Arc application — DataPage lists, CommandDialog toolbar actions, row selection, details components, observable queries, and MVVM. Use when building or modifying a page that lists/displays data, adding a table, wiring Add/Edit/Delete, or connecting a component…

Cratis/AI · 79 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/AI · 100 tokens