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.
npx agentmods add instructions/2389-research/scenario-testing/claude-mdgit clone --depth 1 https://github.com/2389-research/scenario-testingWrote 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.
[](https://agentmods.dev/instructions/2389-research/scenario-testing/claude-md)<a href="https://agentmods.dev/instructions/2389-research/scenario-testing/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/scenario-testing/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01192 | $0.01192 |
| Opus 5 | $0.00596 | $0.00596 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
scenario-testing CLAUDE.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scenario Testing Plugin
Overview
This plugin enforces end-to-end testing with real dependencies instead of mocks. It validates that features actually work by exercising real systems with real data.
Skill Included
scenario-testing
Trigger keywords: test, mock, validate, feature complete, integration test, end-to-end, e2e, testing
When to use:
- Writing tests for new features
- Validating that code actually works
- When tempted to use mocks
- Before declaring work complete
- After fixing bugs
What it does:
- Enforces "NO FEATURE IS VALIDATED UNTIL A SCENARIO PASSES WITH REAL DEPENDENCIES"
- Requires scenarios in
.scratch/directory (gitignored) - Prohibits mocks - must use real dependencies (sandbox/test mode acceptable)
- Ensures scenarios run independently (no ordering dependencies)
- Extracts recurring patterns to
scenarios.jsonl(committed)
Definition of done:
- Scenario in
.scratch/passes with zero mocks - Real dependencies exercised
.scratch/remains gitignored- Patterns extracted to
scenarios.jsonl
Core Principle
The Iron Law: "NO FEATURE IS VALIDATED UNTIL A SCENARIO PASSES WITH REAL DEPENDENCIES"
Mocks create false confidence. Only scenarios exercising real systems validate that code works.
The Truth Hierarchy
- Scenario tests (real system, real data) = TRUTH
- Unit tests (isolated) = human comfort only
- Mocks = lies hiding bugs
"A test that uses mocks is not testing your system. It's testing your assumptions about how dependencies behave."
Required Practices
1. Write Scenarios in .scratch/
# .scratch/test-feature.py - GITIGNORED
def test_user_can_register():
# Hit real database
user = register_user(email="[email protected]")
# Hit real auth service (test mode)
token = authenticate(user)
# Verify against real storage
assert load_user(user.id) is not None
2. Promote Patterns to scenarios.jsonl
{"name":"user-registration","description":"User can register and authenticate","given":"New user credentials","when":"User registers","then":"User exists in DB and can authenticate","validates":"Registration flow"}
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.
- 5d ago First seen · 173 lines · 1,192 tokens per session scan A 620ac08eae41
scenario-testing CLAUDE.md is an instructions file published in the GitHub repository 2389-research/scenario-testing (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,192 tokens to every session, about $0.0060 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.
Other instructions, from other repositories
agentic-playwright api-testing.instructions.md
Instructions for idavidov13/agentic-playwright, covering api testing, critical, instructions, phase 2: define the zod schema and typescript type and phase 3: write the test using the apirequest fixture.
agentic-playwright common-tasks.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai prompt templates for agentic playwright, critical, instructions, phase 1: identify the task category and resolve paths and phase 2: select and customize the matching prompt template.
agentic-playwright ai-native-workflow.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai-native workflow, critical, main workflow (8 phases), phase 4 — confidence-gate format (mandatory) and proposal.
agentic-playwright data-strategy.instructions.md
Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.
agentic-playwright helpers.instructions.md
Instructions for idavidov13/agentic-playwright, covering helpers, critical, file locations, instructions and phase 1: classify what you're adding.
agentic-playwright page-objects.instructions.md
Instructions for idavidov13/agentic-playwright, covering page object model, critical, file locations, page object pattern and rules.