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 dpc00/sublime-mcp --skill sublime-dialogsgit clone --depth 1 https://github.com/dpc00/sublime-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/dpc00/sublime-mcp/sublime-dialogs)<a href="https://agentmods.dev/skills/dpc00/sublime-mcp/sublime-dialogs"><img src="https://agentmods.dev/badge/skills/dpc00/sublime-mcp/sublime-dialogs/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/dpc00/sublime-mcp/sublime-dialogs"><img src="https://agentmods.dev/badge/skills/dpc00/sublime-mcp/sublime-dialogs.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 | $0.00057 | $0.00797 |
| Opus 5.5 | $0.00023 | $0.00319 |
| Sonnet 5.5 | $0.00011 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
sublime-dialogs 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 28d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sublime dialogs: read them, act on them, close them
A dialog is Sublime or a package complaining, and it says what is wrong. One left open disables the editor window and times out most tools, so none is ever left open. Which tools open dialogs is in AGENT_GUIDE.md ("Tools with side effects").
- Look. After a package install, a command that may prompt, or any "main-thread timeout after 5s",
call
list_native_windows(). It works while the main thread is blocked and shows each dialog's text and buttons and whethermain_thread_blockedis true. - Read and act. The text names the cause. Fix the cause, not the symptom: a missing library means
satisfy_libraries; a save prompt for a file you opened means answer it; a package error means read that package's console output and settings. Do not report each dialog to the person; report only what needs a decision or what you could not fix. - Close it at once with
dismiss_native_window: the Cancel button when there is one (Save As, Open and Select Folder have Cancel and no OK), OK for an information dialog,action="close"for a menu or the "Update" window (Sublime shows it even withupdate_checkfalse; never update a portable test build). - If it comes back, stop it coming back. Change what opens it (a setting, a missing dependency, the order of your steps). Closing it again each time is not a fix.
- Look again. Dialogs often come in twos (one per plugin load). Then read
get_consolefor the errors the dialog was about.
Menus
A native menu blocks the main thread like a dialog, and a menu is part of what is being tested, so use the
real one with the real mouse: open it, list_native_windows() (kind menu, note its hwnd),
ui_screenshot(hwnd=...) to see it, ui_click(x, y, hwnd=..., wait_idle_s=60) with x, y counted from the
menu's top-left corner, then check the effect with a normal tool. If no click is wanted, close it with
dismiss_native_window(action="close") as the very next call. Never leave a menu open.
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.
- 28d ago First seen · 48 lines · 57 tokens per session scan A 88e8a83a6521
sublime-dialogs is a skill published in the GitHub repository dpc00/sublime-mcp (4 stars, last pushed 8d ago), licensed MIT. It adds 57 tokens to every session and 797 once invoked, about $0.0002 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 2026-10-19.
sublime-dialogs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sublime-dialogsdpc00/sublime-mcp | Skill | 4 | 8d ago | MIT | A | 57 | Claude Code, Codex |
| report-issue-localcyanheads/obsidian-mcp-server | Skill | 706 | 5d ago | Apache-2.0 | A | 44 | Claude Code |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 2d ago | Apache-2.0 | A | 187 | Claude Code |
| opik-explaincomet-ml/opik-mcp | Skill | 226 | 2d ago | Apache-2.0 | A | 113 | Claude Code |
| lsp-inspectblackwell-systems/agent-lsp | Skill | 180 | today | MIT | A | 126 | Claude Code |
| lsp-refactorblackwell-systems/agent-lsp | Skill | 180 | today | MIT | A | 57 | Claude Code |
| lsp-safe-editblackwell-systems/agent-lsp | Skill | 180 | today | MIT | A | 59 | Claude Code |