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 kolodkin/devpowers --skill screenshotsgit clone --depth 1 https://github.com/kolodkin/devpowersWrote 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/kolodkin/devpowers/screenshots)<a href="https://agentmods.dev/skills/kolodkin/devpowers/screenshots"><img src="https://agentmods.dev/badge/skills/kolodkin/devpowers/screenshots/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/kolodkin/devpowers/screenshots"><img src="https://agentmods.dev/badge/skills/kolodkin/devpowers/screenshots.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 | $0.00063 | $0.01304 |
| Opus 5.5 | $0.00025 | $0.00522 |
| Sonnet 5.5 | $0.00013 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
screenshots 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
screenshots
Four steps.
Invocation
/screenshots [all] [--in DIR] [--out PATH] [--screenshot-on]
all— run the full test suite and report every screenshot. Without it, the report is scoped to the tests worked on in this session (step 1).--in— directory the project's tests write screenshots to. Defaulttest-results/(Playwright JS and pytest-playwright convention). Pass an explicit path if the project writes elsewhere.--out— output HTML path. Default/tmp/e2e-report/index.html.--screenshot-on— additionally force Playwright to save a final-state PNG per test (uses the override config /--screenshot onflag). Off by default.
1. Pick the scope
Default (session scope) — the report demonstrates what was worked on this session, not the whole suite. List the session's tests from:
- Test files you created or modified in this conversation.
- Test files changed on the branch:
git status --porcelainplusgit diff --name-only $(git merge-base HEAD origin/HEAD 2>/dev/null || echo HEAD)— keep the test files (*.spec.*,*.test.*,test_*.py, files undertests//e2e/).
If the list is empty — nothing test-related was touched this session — fall back to the full suite (same as all) and say so when delivering the report.
With all — full suite, no filtering; skip to step 2.
2. Run the e2e tests
If the project has no Playwright tests (no playwright.config.* and no pytest-playwright), stop and tell the user.
Run the tests as-is and harvest the screenshots they already take inline — only the session's test files in session scope, everything with all:
npx playwright test tests/login.spec.ts tests/signup.spec.ts # JS, session scope
npx playwright test # JS, all
pytest tests/test_login.py # Python, session scope
pytest # Python, all
Screenshots land in test-results/ by default. If the project writes elsewhere, pass --in <dir>.
What ships with it
2 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.
- 1mo ago First seen · 118 lines · 63 tokens per session scan A dc3448e0ef20
screenshots is a skill published in the GitHub repository kolodkin/devpowers (2 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,304 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…