SimpleModule: Skill for Claude Code

.claude/skills/verify-feature/SKILL.md

verify-feature is a skill for Claude Code from antosubash/SimpleModule. It costs 96 tokens per session (1,574 once invoked), scanned A, original, MIT.

A gated release-check workflow for a finished feature. It starts the application, tests the feature in a real web browser with Playwright, runs local CI checks, and opens a pull request only if every step passes.

In plain words
What is it for?
Use it to verify a feature on its real route, run browser-based end-to-end tests, check local CI steps, and prepare a pull request.
Why use it?
It prevents untested or failing changes from being sent for review. A failure stops the process and reports the problem instead of opening a pull request.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is antosubash/SimpleModule's own configuration. It tells Claude Code how to work on SimpleModule itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SimpleModule configures →

Reuse

Borrowing it

Nothing to install: this file belongs to antosubash/SimpleModule. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/antosubash/SimpleModule/main/.claude/skills/verify-feature/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/antosubash/SimpleModule

Made for: Claude Code.

Wrote 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.

agentmods badge for verify-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/antosubash/simplemodule/verify-feature/github.svg)](https://agentmods.dev/skills/antosubash/simplemodule/verify-feature)
Your own site
<a href="https://agentmods.dev/skills/antosubash/simplemodule/verify-feature"><img src="https://agentmods.dev/badge/skills/antosubash/simplemodule/verify-feature/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verify-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/antosubash/simplemodule/verify-feature"><img src="https://agentmods.dev/badge/skills/antosubash/simplemodule/verify-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,574 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00096 $0.01574
Opus 5.5 $0.00038 $0.00630
Sonnet 5.5 $0.00019 $0.00315
Haiku 4.5 $0.00010 $0.00157

Measured 1mo ago against content hash 4dcac2871296, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-feature scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Wait for readiness.** Poll the health endpoint with curl (`-k` because the cert is self-signed) until it returns 200, then continue. Cap the wait at 90 seconds.
.claude/skills/verify-feature/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verify-feature

Run this skill after a feature is implemented and committed locally. It is a gated pipeline — each stage must pass before the next runs. If any stage fails, stop, surface the failure, and do NOT open a PR.

Inputs to gather first

Before starting, confirm these from conversation context (do not ask the user unless missing):

  • Feature description — what was implemented (used to pick the page and assertions for stage 2)
  • Page route — the Inertia route (e.g. AuditLogs/Browse) or URL path to exercise
  • Branch — current branch (must not be main)

If route/path is unknown, grep the diff for Inertia.Render("...") calls to infer it.

Stage 1 — Start the application

The host listens on https://localhost:5001 (see CLAUDE.md). Free the port if held, then start the app in the background.

# 1. Kill anything bound to 5001 (TCP). lsof returns nothing if the port is free.
PORT_PIDS=$(lsof -ti tcp:5001 2>/dev/null || true)
if [ -n "$PORT_PIDS" ]; then
  echo "Port 5001 occupied by PID(s): $PORT_PIDS — killing"
  kill -9 $PORT_PIDS
  sleep 1
fi

# 2. Start the host. Use Bash with run_in_background=true so the process keeps running.
dotnet run --project template/SimpleModule.Host

Run the dotnet run command via Bash with run_in_background: true. Capture the shell ID — you will need it to stop the app later.

Wait for readiness. Poll the health endpoint with curl (-k because the cert is self-signed) until it returns 200, then continue. Cap the wait at 90 seconds.

for i in $(seq 1 45); do
  if curl -sk -o /dev/null -w "%{http_code}" https://localhost:5001/ | grep -qE '^(200|302|401)$'; then
    echo "App is up"; break
  fi
  sleep 2
done

If readiness times out, read the background shell's output, surface the error, and abort the skill.

Stage 2 — Verify the feature with playwright-cli

Use the playwright-cli skill's commands directly (already documented in .claude/skills/playwright-cli/SKILL.md). The cert is self-signed; open with --ignore-https-errors via the run-code escape if needed, otherwise just navigate — playwright-cli accepts self-signed certs by default.

Read the full file on GitHub · 159 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. 1mo ago First seen · 159 lines · 96 tokens per session scan A 4dcac2871296

Subscribe to this mod's changes

verify-feature is a skill published in the GitHub repository antosubash/SimpleModule (5 stars, last pushed 19d ago), licensed MIT. It adds 96 tokens to every session and 1,574 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.