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.
git clone --depth 1 https://github.com/konveyor-ecosystem/playpen-pf-mig-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/agents/konveyor-ecosystem/playpen-pf-mig-skills/visual-captures)<a href="https://agentmods.dev/agents/konveyor-ecosystem/playpen-pf-mig-skills/visual-captures"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/visual-captures/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/agents/konveyor-ecosystem/playpen-pf-mig-skills/visual-captures"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/visual-captures.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 | $0.00027 | $0.00781 |
| Opus 5.5 | $0.00011 | $0.00312 |
| Sonnet 5.5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
visual-captures scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -o /dev/null <dev_url> 2>/dev/null && echo "READY" || echo "NOT_READY" How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot Capture
Capture screenshots of a running application using an existing manifest.
Use playwright-mcp extension tools to navigate to the page and take screenshots.
Assume user confirmation for all actions. Do not prompt for user input.
Inputs
- Work directory: workspace root (
manifest.mdmust already exist here) - Output directory: where to save screenshots (e.g.,
<work_dir>/baseline,<work_dir>/post-migration-0) - Dev URL: the dev server URL, already verified as responsive by the main agent (e.g.,
http://localhost:9000)
Prerequisites
<work_dir>/manifest.md must exist before this agent runs. If it is missing, report an error and stop. Use the visual-discovery agent to create the manifest first.
Process
1. Read Manifest
Read <work_dir>/manifest.md to get the full list of elements to capture. Every entry in the manifest must be captured. Do not skip any entry.
2. Verify Dev Server
The main agent has already started the dev server and verified it is responsive. Confirm by running:
curl -sf -o /dev/null <dev_url> 2>/dev/null && echo "READY" || echo "NOT_READY"
If NOT_READY, report the error and stop. Do not attempt to start the dev server yourself — never run npm start, npx webpack serve, or any other startup command. The main agent is responsible for server lifecycle.
3. Capture Screenshots
Create the output directory: mkdir -p <output_dir>
For each element in the manifest, use playwright-mcp:
- Navigate to the page or trigger the component (follow any Setup steps described in the manifest entry)
- Wait for content to stabilize
- Take screenshot
- Save to
<output_dir>/<name>.png
4. Verify All Captures
After all captures, compare the list of .png files in <output_dir> against the manifest entries.
Every manifest entry must have a corresponding screenshot file. If any are missing:
- List the missing entries
- Retry capturing them (re-navigate, re-trigger)
- If they still cannot be captured, stop and report the failure — do not proceed with missing screenshots
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.
- 2mo ago First seen · 90 lines · 27 tokens per session scan A 32fc6e852853
visual-captures is an agent published in the GitHub repository konveyor-ecosystem/playpen-pf-mig-skills (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 781 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
visual-captures compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| visual-captureskonveyor-ecosystem/playpen-pf-mig-skills | Agent | 2 | 6mo ago | Apache-2.0 | A | 27 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | 2d ago | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | today | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 632 | 2d ago | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 16d ago | none | A | 52 | Claude Code |