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 s243a/SciREPL-MCP --skill scirepl-playwrightgit clone --depth 1 https://github.com/s243a/SciREPL-MCPWrote 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/s243a/scirepl-mcp/scirepl-playwright)<a href="https://agentmods.dev/skills/s243a/scirepl-mcp/scirepl-playwright"><img src="https://agentmods.dev/badge/skills/s243a/scirepl-mcp/scirepl-playwright/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/s243a/scirepl-mcp/scirepl-playwright"><img src="https://agentmods.dev/badge/skills/s243a/scirepl-mcp/scirepl-playwright.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 | $0.00677 |
| Opus 5.5 | $0.00011 | $0.00271 |
| Sonnet 5.5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
scirepl-playwright 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 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.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SciREPL Playwright workflow
Use this skill when a task requires running, inspecting, or troubleshooting a SciREPL workbook through the Playwright driver.
Session rule
Complete one workflow in one scirepl_* browser session. A separate general
browser or Playwright MCP normally has different storage and in-memory state.
Only treat another client as the same browser when it explicitly attaches to
the CDP URL with connectOverCDP.
Standard workflow
1. scirepl_connect
2. scirepl_install_package or scirepl_import_file, when needed
3. scirepl_run_all_cells_ui for visible testing, or scirepl_run_all_cells for batch execution
4. scirepl_get_cell_outputs_detailed
5. scirepl_get_visible_state and scirepl_screenshot for supporting evidence
6. scirepl_disconnect
Prefer scirepl_run_all_cells_ui when the user mentions the menu, visible
output, warnings, browser behaviour, or screenshots.
Diagnosing output
- Reproduce the issue through the requested run path.
- Read
scirepl_get_cell_outputs_detailed; it combines app-model output with DOM-rendered text and includesOut [n]labels where present. - Capture a screenshot for layout and rendering evidence.
- Use console messages from
scirepl_get_visible_stateas supporting evidence, not as a substitute for the visible cell result. - If the user sees output that the tool omits, treat that as an instrumentation gap and inspect the driver before concluding the output is absent.
Browser-state investigation
For stale assets, cache, storage, workers, or PWA-update issues:
1. scirepl_connect(debugMode: true, remoteDebuggingPort: 9223)
2. scirepl_get_browser_debug_info
3. Continue the ordinary workflow in that same session
4. If necessary, attach a CDP-capable debugger to the reported URL
Opening the debugger URL as a web page is not equivalent to attaching through CDP.
Supported kernels
Python, R, TypR, SWI-Prolog, Bash, JavaScript, Lua, and ClojureScript.
Local package iteration
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 · 77 lines · 27 tokens per session scan A 971253158537
scirepl-playwright is a skill published in the GitHub repository s243a/SciREPL-MCP (0 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 677 once invoked, about $0.0001 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.
scirepl-playwright compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scirepl-playwrights243a/SciREPL-MCP | Skill | 0 | 2d ago | MIT | A | 27 | Claude Code, Codex |
| phaserkyh/vibedgames | Skill | 61 | 2d ago | MIT | A | 42 | Claude Code |
| interactive-map-builderxlbaoxl/interactive-map-builder | Skill | 23 | 1mo ago | MIT | A | 203 | Codex |
| photonforge-gui-automationflexcompute/plugin-marketplace | Skill | 9 | 1mo ago | none | A | 172 | Claude Code |
| photonforge-live-viewerflexcompute/plugin-marketplace | Skill | 9 | 1mo ago | none | A | 187 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | today | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 83 | Claude Code |