test-scenarios

test-scenarios is a skill for Claude Code from ivanhoinacki/team-exp-claude-config. It costs 132 tokens per session (3,162 once invoked), scanned A, original, MIT.

A testing procedure that validates a feature with real data and realistic usage before it is committed. It includes checking the environment, preparing test data, running automated tests, and performing manual smoke tests, which are quick checks of the main user path.

In plain words
What is it for?
It helps verify Docker, VPN, databases, and other required services; seed test data; run unit and integration tests; and check positive, negative, and boundary scenarios.
Why use it?
It catches failures caused by missing services, bad test data, edge cases, or incorrect assumptions that unit tests alone may miss. It provides a quality checkpoint before changes are committed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit It helps verify Docker, VPN, databases, and other required services; seed test data; run unit and integration tests; and check positive, negative, and boundary scenarios.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivanhoinacki/team-exp-claude-config/test-scenarios
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.

Any agent
npx skills add ivanhoinacki/team-exp-claude-config --skill test-scenarios
Clone the repo
git clone --depth 1 https://github.com/ivanhoinacki/team-exp-claude-config

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 test-scenarios

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/test-scenarios/github.svg)](https://agentmods.dev/skills/ivanhoinacki/team-exp-claude-config/test-scenarios)
Your own site
<a href="https://agentmods.dev/skills/ivanhoinacki/team-exp-claude-config/test-scenarios"><img src="https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/test-scenarios/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 test-scenarios

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivanhoinacki/team-exp-claude-config/test-scenarios"><img src="https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/test-scenarios.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,162 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 $0.00132 $0.03162
Opus 5 $0.00066 $0.01581
Sonnet 5 $0.00026 $0.00632
Haiku 4.5 $0.00013 $0.00316

Measured 11d ago against content hash f8fdbfbde1c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

test-scenarios 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 11d 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.

allowed-tools: Bash(git *), Bash(gh *), Bash(docker *), Bash(curl *), Bash(yarn *), Bash(npx *), Bash(node *), Bash(psql *), Read, Write, Edit, Grep, Glob, Agent
skills/test-scenarios/SKILL.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 0: Vault RAG (MANDATORY, BEFORE any Read/Grep)

You MUST call query_vault(query, service_filter) BEFORE reading codebase files or external sources. This is enforced by hook. No exceptions.


Test Scenarios -- Real Validation Before Commit

Validate that the feature works with real data, not just unit test mocks. Covers environment setup, test data seeding, automated tests, and manual smoke tests.

When to Use

After /code-review approves, before /commit. This is a quality gate.

/feature-dev -> /deslop -> /code-review -> /test-scenarios -> /commit -> /create-pr

Common Agent Mistakes

  1. Running tests without checking infra: Tests fail because Docker containers are down, not because code is wrong. Always verify environment first
  2. Testing only happy path: Missing edge cases, error paths, empty arrays, null values. Every scenario needs positive + negative + edge
  3. Assuming staging data matches expectations: Staging data changes daily. Always verify test data exists before running smoke tests
  4. Not asking user for VPN/tunnel: DB access and staging APIs require VPN. Always ask if VPN is connected before any remote operation
  5. Skipping test data setup: Running integration tests against empty tables. Seed or verify data exists first
  6. Running against empty local DB for provider features: When testing features that depend on real provider data (SSC/CMC sync, images, pickup points), the local DB is empty. ALWAYS ask user for VPN + le aws login, then set up staging DB tunnel via le-tunnel.sh and configure .env to point to the tunnel BEFORE starting the service. Without this, images won't load (Cloudinary IDs not in local DB) and synced data won't exist

Phase 1: Environment Verification

1.1 Local Infrastructure

# Check Docker containers
docker ps --format '{{.Names}}' | grep -E 'postgres|redis|nginx'

# Check which DB the service uses (from MEMORY.md Quick Configs)
# svc-experiences: PG16 :5439
# svc-ee-offer: PG14 :5436
# svc-order: PG (needs .env)
# svc-car-hire: Prisma

Read the full file on GitHub · 385 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. 11d ago First seen · 385 lines · 132 tokens per session scan A f8fdbfbde1c6

Subscribe to this mod's changes

test-scenarios is a skill published in the GitHub repository ivanhoinacki/team-exp-claude-config (2 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 3,162 once invoked, about $0.0007 per session on Opus 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 2026-08-31.