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 mthines/agent-skills --skill preview-specgit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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/mthines/agent-skills/preview-spec)<a href="https://agentmods.dev/skills/mthines/agent-skills/preview-spec"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/preview-spec/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/mthines/agent-skills/preview-spec"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/preview-spec.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00223 | $0.03154 |
| Opus 5 | $0.00112 | $0.01577 |
| Sonnet 5 | $0.00045 | $0.00631 |
| Haiku 4.5 | $0.00022 | $0.00315 |
Grade A, and why
preview-spec 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preview Spec
Attach an executable UI verification spec to a pull request, then run it against the live preview deployment.
A reviewer verifies a UI change by clicking through the preview.
preview-spec turns that click-through into an artifact an agent can follow: a short spec in the PR description, run against the deployed preview by aw-tester, reporting pass or fail.
This
SKILL.mdis a thin index. Detailed procedures live inrules/*.mdandtemplates/*.md. Each operation loads only what it needs.
What this skill reuses
This skill owns three things and reuses the rest.
| Concern | Owner |
|---|---|
The spec grammar (WHEN/THEN/AND, the locator mini-grammar, url:, network:) |
aw-tester — specs.md.template. This skill references it and never forks it. |
| The spec-run contract (locator ladder, auth semantics, verdict schema) | spec-run-contract.md — the engine-agnostic contract both runners implement. |
| The runners + the compact verdict | Two, one contract: aw-tester (Playwright sub-agent) and aw-tester-chrome (in-session Chrome). run --driver picks one. |
The browser context (base_url, auth, fixtures) |
aw-target.yml — aw-target.yml.template. |
| The two-way lessons loop | aw-tester-lessons (locator friction, existing) + preview-spec-lessons (navigation / spec-quality friction, new). See rules/memory.md. |
| Embedding the spec in the PR body (marker + collapsed block, ceiling exemption) | this skill — rules/spec-format.md. |
| Resolving the PR's preview URL (GitHub deployments API) | this skill — rules/preview-url-resolution.md. |
| The author + run orchestration | this skill — this file + rules/runner.md. |
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.
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 · +19 lines 797b27e155f3
- 7d ago Changed 68f85d3a3fcf
- 8d ago First seen · 128 lines · 223 tokens per session scan A 353eb5660ff8
preview-spec is a skill published in the GitHub repository mthines/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 223 tokens to every session and 3,154 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
tdd-workflow
Runs the full TDD workflow for a TypeScript/JavaScript feature — user journeys to test cases, unit tests (Jest/Vitest + Testing Library), API/integration tests, Playwright E2E, and a coverage gate wired into CI. Use when building a Next.js/React/Node feature end to end, not just a single unit test, or when asked to…
e2e-testing
Guides Playwright end-to-end test design — Page Object Model, CI configuration, and flaky test diagnosis. Use when writing browser-based end-to-end tests, debugging a test that fails intermittently, setting up Playwright CI configuration, or reviewing E2E test code for race conditions and arbitrary waits.
browser-testing-with-devtools
Use Chrome DevTools MCP to inspect, debug, and verify anything that runs in a browser — DOM structure, console errors, network requests, performance traces, and accessibility. Use when building or fixing browser UI, diagnosing a runtime bug that isn't visible from source code alone, or verifying a fix actually works…
specification-compliance-review
Use this skill when an implementation is described as partial, passing, or complete and the task is to determine whether it actually satisfies an explicit specification. This is not a generic code review and not a re-run of the test suite. The central question is: does every normative requirement have both a correct…
test-conversion-reviewer
Reviewer for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to review their work while removing complex Browser dependencies from tests.
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…