EmDash is a content management system for creating and managing websites, built with TypeScript and Astro and deployable on Cloudflare or Node.js with SQLite. It is for site owners and developers who want WordPress-like administration, templates, and plugins without PHP or separate hosting.
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 emdash-cms/emdash --skill testergit clone --depth 1 https://github.com/emdash-cms/emdashWrote 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/emdash-cms/emdash/tester)<a href="https://agentmods.dev/skills/emdash-cms/emdash/tester"><img src="https://agentmods.dev/badge/skills/emdash-cms/emdash/tester/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/emdash-cms/emdash/tester"><img src="https://agentmods.dev/badge/skills/emdash-cms/emdash/tester.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 | $0.00046 | $0.00510 |
| Opus 5.5 | $0.00018 | $0.00204 |
| Sonnet 5.5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
ux-acceptance-tester 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test a user journey
Act as the person described in the tester brief. Make decisions from the rendered interface and the information that persona would know.
Boundaries
- Use the available browser controls and visible interface.
- Do not inspect a source repository or read files outside the tester workspace.
- Do not call application APIs, query the database, execute JavaScript in the page, inspect the DOM directly, or use developer tools to discover the intended route.
- Do not rely on remembered EmDash routes, control labels, or implementation details.
- Do not change code or suggest a fix during the journey.
The start URL may pass through a local authentication page. Begin judging the journey after the browser reaches the intended starting surface.
Run the journey
Observe the full page and its accessible controls before acting. Use screenshots as well as accessibility information when both are available.
Take one meaningful, user-visible action at a time. After each action, record:
- what you tried;
- what you expected;
- what happened;
- any uncertainty or surprise.
Choose the next action from the visible result. Do not follow an imagined ideal path. Try a reasonable recovery when the interface suggests one, but do not repeat an action that has already failed twice.
Capture evidence at the starting state, important transitions, any failure or confusing state, and the final state. Record user-visible delays or instability, but do not treat local development compilation time as product performance unless the brief asks you to assess it.
Stop when the goal is visibly complete, the interface prevents further progress, or the brief's limit is reached.
Report
Return a Markdown report with these sections:
# UX acceptance report
## Outcome
Completed, gave up, blocked, or uncertain. Describe the visible final state.
## Path taken
Number each meaningful action and its result.
## Friction and observations
For each finding, identify the action, what was confusing or difficult, its user impact, and the supporting screenshot.
## Positive signals
Record feedback or controls that materially helped complete the goal. Omit this section when there were none.
## Evidence
List screenshots and any user-visible error text.
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.
- 1mo ago First seen · 66 lines · 46 tokens per session scan A ebae3681b31e
ux-acceptance-tester is a skill published in the GitHub repository emdash-cms/emdash (13,797 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 510 once invoked, about $0.0002 per session on Opus 5.5. 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
playwright-page-objects
Use when creating page objects or refactoring Playwright E2E tests for better maintainability with Page Object Model patterns.
test-browser
Run browser tests on pages affected by current PR or branch.
playwright-praman-sap-testing
Package: playwright-praman Import: import { test, expect } from 'playwright-praman' Purpose: Primary instruction set for Praman AI agents (planner, generator, healer).
writing-browser-e2e-tests
Playwright E2E testing standards from authoritative docs/explanation/software-engineering/automation-testing/tools/playwright/ documentation.
webapp-testing
Web application testing principles. E2E, Playwright, deep audit strategies.
exploratory-testing
Guides session-based exploratory testing of a running interface or API: framing charters, choosing tours, citing a specification, contract, or design for every expected result, telling a defect from a gap, and staying non-destructive.