build-scenario-tests

build-scenario-tests is a skill for Codex from tamdogood/builder-essential-skills. It costs 104 tokens per session (1,331 once invoked), scanned A, original, MIT.

A workflow for turning a short Markdown behavior description into a deterministic automated test in an existing code repository. It uses the repository’s own testing tools and keeps the description linked to the test.

In plain words
What is it for?
Use it to turn acceptance criteria or Given/When/Then scenarios into executable tests. It helps verify one user-visible behavior at a time.
Why use it?
It removes the guesswork of choosing a test setup, inputs, selectors, and checks when working in an unfamiliar project. It also keeps the original requirement traceable to the code that tests it.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it to turn acceptance criteria or Given/When/Then scenarios into executable tests. It helps verify one user-visible behavior at a time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tamdogood/builder-essential-skills/build-scenario-tests
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 tamdogood/builder-essential-skills --skill build-scenario-tests
Clone the repo
git clone --depth 1 https://github.com/tamdogood/builder-essential-skills

Made for: Codex.

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 build-scenario-tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/tamdogood/builder-essential-skills/build-scenario-tests/github.svg)](https://agentmods.dev/skills/tamdogood/builder-essential-skills/build-scenario-tests)
Your own site
<a href="https://agentmods.dev/skills/tamdogood/builder-essential-skills/build-scenario-tests"><img src="https://agentmods.dev/badge/skills/tamdogood/builder-essential-skills/build-scenario-tests/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 build-scenario-tests

Your own site · 80×15
<a href="https://agentmods.dev/skills/tamdogood/builder-essential-skills/build-scenario-tests"><img src="https://agentmods.dev/badge/skills/tamdogood/builder-essential-skills/build-scenario-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00104 $0.01331
Opus 5 $0.00052 $0.00665
Sonnet 5 $0.00021 $0.00266
Haiku 4.5 $0.00010 $0.00133

Measured 11d ago against content hash d429a1536757, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

build-scenario-tests 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (examples/test_cli_expired_session.py, examples/web-workspace-invite.spec.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/build-scenario-tests/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Scenario Tests

Compile one small behavior contract into deterministic, repository-native test code. Understand the host project before choosing a harness, command, fixture, selector, or assertion.

Operating contract

  • Treat repository instructions and existing tests as authoritative.
  • Keep each scenario focused on one behavior and one reason to fail.
  • Compile into the test stack the repository already uses. Add a dependency only when no suitable harness exists and the user accepts the tradeoff.
  • Make setup, inputs, actions, and expected results deterministic.
  • Prefer public behavior over implementation details. Assert what a user or external caller can observe.
  • Keep the Markdown scenario beside the test or in the repository's established specification directory. Record the mapping in both artifacts.
  • Never weaken an assertion merely to make a test pass.

Workflow

1. Pass the repository-understanding gate

Read the nearest AGENTS.md or equivalent instructions, product README, contribution guide, manifests, test configuration, and the smallest relevant product documentation. Use repository search to find the implementation entry point, neighboring tests, fixtures, stable selectors, and validation commands. Trace the relevant action from its public entry point through the state boundary to the observable result. Do not read the entire tree without a reason.

Before editing, be able to state:

product surface:
behavior source:
relevant architecture and data flow:
runtime or start command:
existing test runner:
nearest tests to imitate:
fixture and state-isolation strategy:
narrow validation command:
full validation command:
known trust or destructive boundaries:

If a material field is unknown, search again. If the repository does not answer it, expose the gap and ask only for the missing product decision. Do not invent commands, selectors, credentials, or expected behavior.

2. Normalize the scenario

Read references/scenario-format.md. If the user provided prose, rewrite it into that contract without changing its intent.

Read the full file on GitHub · 158 lines

Files

What ships with it

7 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. 11d ago First seen · 158 lines · 104 tokens per session scan A d429a1536757

Subscribe to this mod's changes

build-scenario-tests is a skill published in the GitHub repository tamdogood/builder-essential-skills (196 stars, last pushed 25d ago), licensed MIT. It adds 104 tokens to every session and 1,331 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

refactor-safely

Restructure existing code safely without changing externally observable behavior. Composes context, design, architecture, code quality, and testing guardrails into a characterization-first refactoring workflow. Use when the user says 'refactor this', 'clean this up', 'untangle this module', 'move this to the right…

techygarg/lattice · 82 tokens

requirement-quality

Apply requirement quality principles when generating or validating feature specifications. Enforces feature completeness, scenario structure, AC verifiability, feature independence, and implementation slice quality. Use when writing feature specs, validating existing requirements, or when the user mentions 'validate…

techygarg/lattice · 106 tokens

test-quality

Apply test quality principles when generating or reviewing test code. Enforces Arrange-Act-Assert structure, one behavior per test, assertion quality, test isolation, meaningful naming, and test data management. Use when writing tests, reviewing test code, or when the user mentions 'write tests', 'test this', 'test…

techygarg/lattice · 145 tokens

herdr-benchmark-pane

Run Skill Heaven benchmark probes and side-by-side posture comparisons in visible Herdr panes. Use whenever comparing postures (floor, product-floor, curated, native), doors (claude-zero, pi-zero, codex-zero), or harnesses, and the operator must be able to watch every arm run.

gaia-research/gaia-skill-heaven · 67 tokens

phx-work

Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.

oliver-kriska/claude-elixir-phoenix · 43 tokens

lab:autoresearch

Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.

oliver-kriska/claude-elixir-phoenix · 52 tokens