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 skills add jstoup111/ai-conductor --skill writing-system-testsgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/skills/jstoup111/ai-conductor/writing-system-tests)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/writing-system-tests"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/writing-system-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.
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/writing-system-tests"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/writing-system-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00067 | $0.09026 |
| Opus 5 | $0.00034 | $0.04513 |
| Sonnet 5 | $0.00013 | $0.01805 |
| Haiku 4.5 | $0.00007 | $0.00903 |
Grade A, and why
writing-system-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 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.
How it starts
The opening of the file, as written. The whole thing — 711 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Acceptance Tests
Overview
Generate failing acceptance specs from user stories in .docs/stories/*.md. Each acceptance
criterion (happy AND negative paths) receives a concrete coverage disposition. Only the criteria
that need acceptance/system coverage become generated specs; those specs are written BEFORE
implementation and are the RED phase of BDD.
Correctness gate: a test encodes an expected-behavior claim. Per the /verify-claims protocol,
if a spec rests on an assumption about what "correct" means that is not pinned by the story's
acceptance criteria, the FR, or the ADR, surface it with its confidence and HARD-BLOCK for operator
approval (HALT if autonomous) rather than freezing a guess into a passing/failing assertion.
This skill is language- and framework-agnostic. It describes what acceptance tests to
write and why; the concrete syntax, test runner, file layout, and fixture mechanism come
from the project's own conventions. Detect those from the loaded tech-context (see
tech-context/) or from the existing test suite, and follow them — exactly as the /tdd skill
defers to "stack test conventions."
Detect project shape and generate the right kind of acceptance test:
| Project Shape | Acceptance Test Type | Exercises |
|---|---|---|
| Headless / API (no UI) | HTTP / request-level acceptance tests | HTTP requests, status codes, serialized (JSON/XML/etc.) responses |
| Has a frontend / full-stack | End-to-end (E2E) / UI tests | A real UI driver — browser, native, or TUI — navigation and user-visible assertions |
The test framework and paths are the project's, not this skill's. Place and name specs per the project's conventions. Illustrative mappings (adapt to whatever the project actually uses):
| Stack | HTTP-level acceptance | E2E / UI |
|---|---|---|
| Ruby + RSpec | spec/integration/ (type: :request) |
spec/system/ (Capybara) |
| Python + pytest | tests/integration/ (httpx/requests) |
tests/e2e/ (Playwright/Selenium) |
| JS/TS + Jest/Vitest | test/integration/ (supertest) |
test/e2e/ (Playwright/Cypress) |
| Go | *_integration_test.go (net/http/httptest) |
e2e/ (chromedp/rod) |
What ships with it
1 file 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.
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.
- 3d ago Changed · -9 lines 7e718a25eea9
- 4d ago Changed · +2 lines 545e4815c412
- 10d ago First seen · 718 lines · 67 tokens per session scan A d7965a009561
writing-system-tests is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 9,026 once invoked, about $0.0003 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 skills, from other repositories
nw-ad-critique-dimensions
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof.
nw-bdd-methodology
BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation.
testing
TDD/BDD testing principles. Use when writing tests, reviewing test coverage, setting up testing, or discussing test strategy and test architecture.
review-screenshot
A standard workflow for taking screenshots to check a user interface, using a dedicated review process for different verification modes.
testing-expert
Expert-level software testing with unit tests, integration tests, E2E tests, TDD/BDD, and testing best practices. Use when the user mentions TDD, BDD, unit tests, integration tests, or end-to-end tests, or when the task involves Testing Fundamentals, Unit Testing, Integration Testing, or End-to-End Testing.
qa
QA workflow that validates a running application against Gherkin user stories. Use when running /qa or /qa:new-story, writing user stories under docs/user-stories/, decomposing Gherkin scenarios into Playwright and Tidewave validation work, mapping Given/When/Then to a RED/GREEN TDD loop, or filing observed behavior…