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 agentmods add skills/darknodebros/elesync/testing-elesync-webnpx skills add darknodebros/EleSync --skill testing-elesync-webgit clone --depth 1 https://github.com/darknodebros/EleSyncWhat 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 | $0.00023 | $0.00927 |
| Opus 5 | $0.00012 | $0.00464 |
| Sonnet 5 | $0.00005 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
Testing EleSync Web Dashboard 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 2d 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.
Testing the EleSync Web Dashboard
Devin Secrets Needed
- None beyond standard Windows admin access.
Required tools / paths
- Python environment at
C:\devin\python\python.exe;eleis installed asC:\devin\python\Scripts\ele.exeand is not onPATH. - Chrome for Testing binary at
C:\devin\chrome\chrome-win64\chrome.exe. pyautogui+Pilloware useful for UI automation; they are not preinstalled.
Setup
- Install/refresh dependencies:
python -m pip install -e .[dev] python -m pip install pyautogui Pillow - Create an isolated
APPDATAdirectory and a temp vault directory. - Write
config.jsonat%APPDATA%\EleSync\config.json:
Use Python's{"vault_dir": "<VAULT>", "first_run_setup": true}json.dump(no BOM) to avoid UTF-8 BOM decode failures.
Launching the server
set APPDATA=C:\Users\Administrator\AppData\Local\Temp\<test>\appdata
C:\devin\python\Scripts\ele.exe --vault <VAULT> web --no-browser --port 7477
Watch out: on the first launch ele may prompt for a language choice and wait for stdin. In a batch file this can hang; run it inside an interactive or PTY-backed shell so the default (English) is selected, or pre-configure the language. Wait until netstat -ano | findstr 7477 shows LISTENING.
Browser automation tips
- Do not rely on the DevTools/CDP helper in this environment; Chrome for Testing does not expose a usable CDP endpoint for the agent.
- Use
pyautoguiwith a fresh Chrome profile (--no-first-run --start-maximized --user-data-dir=<profile>). - Screen resolution is 1280x720; maximize Chrome to keep UI coordinates stable.
- Keyboard shortcuts in the dashboard are the most reliable navigation:
n→ Add memory (only works when no input is focused)Ctrl+K, typeAdd memoryorSearch,Enter→ command palette navigation/→ focus search input
- The first-run modal can be dismissed by clicking the purple Finish setup button (with the passcode checkbox unchecked).
- The content textarea in the Add page is a large white box centered around screen
(525, 283)at 1280x720. - The Save memory button is the purple button in the lower-left of the Add page.
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.
- 2d ago First seen · 66 lines · 23 tokens per session scan A 3dde60848f10
Testing EleSync Web Dashboard is a skill published in the GitHub repository darknodebros/EleSync (4 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 927 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
tui-tester
Expert guidance for testing Gemini CLI behavior and visual output using terminal automation.
testing
Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.
vscode-visual-regression
Write Storybook stories and visual regression tests for the Kilo VS Code extension webview UI.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
e2e-deployment-skill
Use this deployment skill to verify shared skills load during Playwright startup.