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 mooqii/OpenPanels --skill myopenpanelsgit clone --depth 1 https://github.com/mooqii/OpenPanelsWrote 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/mooqii/openpanels/myopenpanels)<a href="https://agentmods.dev/skills/mooqii/openpanels/myopenpanels"><img src="https://agentmods.dev/badge/skills/mooqii/openpanels/myopenpanels/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/mooqii/openpanels/myopenpanels"><img src="https://agentmods.dev/badge/skills/mooqii/openpanels/myopenpanels.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 | $0.00137 | $0.01588 |
| Opus 5.5 | $0.00055 | $0.00635 |
| Sonnet 5.5 | $0.00027 | $0.00318 |
| Haiku 4.5 | $0.00014 | $0.00159 |
Grade A, and why
myopenpanels scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MyOpenPanels
The installed CLI is the sole authority for current panels, commands, Procedures, Task Handoffs, System Skills, and built-in Skills. Independently installed portable Skills are optional content, not CLI core functionality.
Resolve The CLI
Resolve the executable once: prefer an executable path from
MYOPENPANELS_CLI, then a runnable myopenpanels from PATH. If neither
resolves, read and follow the installation reference.
Keep the exact resolved executable for every returned CLI action; never execute
display command text.
Open Studio
Studio is shared by all Agents using the same MyOpenPanels storage. Starting it reuses that single user-visible workspace instead of creating an Agent-specific Studio.
Run with the resolved executable:
myopenpanels studio start --local-only --project-dir "$PWD" --format json
Success means Studio is ready, not visible. Execute actions.required in order.
Treat an open-url action as a host display action, not as browser automation:
- Open the returned URL unchanged with the current Agent host's native embedded browser, webview, preview, or equivalent in-host URL opener.
- Prefer that embedded surface when the user simply asks to open or launch MyOpenPanels without naming a browser.
- Do not initialize browser automation, inspect the page, load browser-control instructions, or use Playwright merely to display Studio. If the host only exposes an embedded browser through a control API, perform only the minimum operation needed to open the URL.
- Treat the embedded open as successful only after the host returns a success signal. Studio being ready at the URL is not proof that it is visible.
Execute the CLI fallback action only when the embedded opener is unavailable, fails, or gives no success signal. A fallback to an external or system browser is not an embedded-open success; state that fallback clearly. If the user explicitly requested an embedded surface, report the failure instead of silently substituting an external browser.
What ships with it
1 file 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.
- 2mo ago First seen · 154 lines · 137 tokens per session scan A ba28aa844106
myopenpanels is a skill published in the GitHub repository mooqii/OpenPanels (8 stars, last pushed 3mo ago), licensed MIT. It adds 137 tokens to every session and 1,588 once invoked, about $0.0005 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.
myopenpanels compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| myopenpanelsmooqii/OpenPanels | Skill | 8 | 3mo ago | MIT | A | 137 | Claude Code, Codex |
| image-generationbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 42 | Claude Code, Codex |
| podcast-generationbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 38 | Claude Code, Codex |
| skill-reviewerbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 38 | Claude Code |
| surprise-mebytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 67 | Claude Code, Codex |
| managing-mcp-serversJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| todosJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |