test-feature

A command that creates tests for a Kotlin Multiplatform feature by first examining the feature's structure, data, repositories, view models, and screens.

In plain words
What is it for?
Use `/test-feature {featurename}` to generate tests for a KMP feature's data flow and user-interface logic.
Why use it?
It reduces the work of understanding an existing feature before writing tests and adapts the test plan to details such as pagination or single-item results.

Command for Claude Code

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 commands/thisissadeghi/kmpilot/test-feature
Clone the repo
git clone --depth 1 https://github.com/ThisIsSadeghi/KMPilot

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,329 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 $0.00008 $0.02329
Opus 5 $0.00004 $0.01164
Sonnet 5 $0.00002 $0.00466
Haiku 4.5 $0.00001 $0.00233

Measured 3d ago against content hash bae0ca8dff1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-feature 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 3d 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.

.claude/commands/test-feature.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Feature Tests

Usage: /test-feature {featurename}

Phase 1: Discovery (Direct Execution)

1.1 Detect Namespaces

grep "namespace" feature/{featurename}/build.gradle.kts     # PKG_PREFIX
grep "namespace" core/common/build.gradle.kts        # CORE_COMMON_PKG
grep "namespace" core/data/build.gradle.kts          # CORE_DATA_PKG

1.2 Extract Context (YAML Only)

Glob: feature/{featurename}/src/commonMain/kotlin/**/*.kt

Extract 5-line YAML summaries (not full code):

entities: [{name, fields}]
dataSource: {interface, implementation, methods}
repository: {interface, implementation, dependencies}
viewModel: {class, dependencies, actions, flow_name, state_slot}  # see detection rules
screen: {composable, rootComposable, callbacks}

# Capability flags (drive conditional template sections):
hasDto: true|false              # true if data/model/*Dto.kt exists OR DTO class found alongside entities
hasPagination: true|false       # true if {Feature}Response with results/count/next/previous fields exists
successValueShape: list|single  # list = repository returns Either<List<T>>; single = Either<T> (non-list)

Detection rules:

  • flow_name: read the ViewModel's public flow property — match val (\w+)\s*=\s*_\w+\.asStateFlow\(\). Under Rule 11 convention, this is uiModel. Pass the matched name (e.g. uiModel, or uiState for legacy features) to all presentation agents.
  • state_slot: read {Feature}UiModel.kt for val (\w+)State:\s*UiState< — the slot prefix (e.g. data, submit, fetch) is what test agents substitute for {state}. If multiple slots exist, pass the primary one; default data.
  • hasDto: glob feature/{featurename}/src/commonMain/kotlin/**/model/*Dto.kt → if any match, true.
  • hasPagination: grep data class .*Response.*results.*count in data/model/*.kt.
  • successValueShape: read the repository interface return type. Either<List<...>>list; Either<...> (anything else) → single. (Repository returns Either<DTO> directly — Rule 11.)

Read the full file on GitHub · 241 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. 3d ago First seen · 241 lines · 8 tokens per session scan A bae0ca8dff1a

Subscribe to this mod's changes

test-feature is a command published in the GitHub repository ThisIsSadeghi/KMPilot (56 stars, last pushed 25d ago), licensed MIT. It adds 8 tokens to every session and 2,329 once invoked, about $0.0000 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 2026-08-30.