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 SirAllap/agentglass --skill ui-controlgit clone --depth 1 https://github.com/SirAllap/agentglassWrote 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/sirallap/agentglass/ui-control)<a href="https://agentmods.dev/skills/sirallap/agentglass/ui-control"><img src="https://agentmods.dev/badge/skills/sirallap/agentglass/ui-control/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/sirallap/agentglass/ui-control"><img src="https://agentmods.dev/badge/skills/sirallap/agentglass/ui-control.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 | $0.00127 | $0.02826 |
| Opus 5.5 | $0.00051 | $0.01130 |
| Sonnet 5.5 | $0.00025 | $0.00565 |
| Haiku 4.5 | $0.00013 | $0.00283 |
Grade A, and why
ui-control 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 6d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving agentglass's own screen
The window the person works in has panels (Settings, the machine panel, the
bench, the Git modals, the file finder) and settings. agentglass-ui is your
door to them: the same list of doors a Stream Deck button uses, with a name on
every call so the person can see in the action log that it was you.
agentglass-ui list # every door, its level, its arguments
agentglass-ui state # what is open now; which panels `read` describes
agentglass-ui read chat # one panel's state, shown nowhere
agentglass-ui open settings.open --arg page=diff --arg row=wrap-long-lines # quiet: a chip if they are typing
agentglass-ui open --now settings.open --arg page=diff # they said "show me": at once
agentglass-ui settings list # what you may read and write
agentglass-ui settings get diff.wrap
agentglass-ui settings set diff.wrap true
agentglass-ui --as my-agent read view # put a name on the call
As an MCP server: claude mcp add agentglass-ui -- agentglass-ui-mcp. One tool per
door (ui_settings_open, ui_read, ui_settings_set, ...), and the list comes
from the running app, so it is always the doors this version has. Set
AGENTGLASS_UI_AS to the name your calls carry.
What you can open: every view and Settings page, one plugin's own page
(settings.plugin), the machine panel, project picker, window switcher, the
bench, a file in the viewer, the Git modals (insights, bisect, the git palette,
compare, blame, and the rebase editor, which only draws the plan), one event or
session the window holds (event.open, session.open), the running version's
release notes (whatsnew.open), the Lantern schedule dialog, the Terminal's
Resume list, and what the pane chords open for the focused terminal pane
(pane.open). Opening only shows: starting a rebase, saving a schedule,
resuming a session is the person's click. Not doors, on purpose: the people
picker, the Rescue modal and the menus inside a panel; agentglass-ui list is
the truth.
What you can read: agentglass-ui read <panel> for view, chat, bench, gates and
the Settings panes (diff, terminal, browser, notifications, prefs, rail, keys,
tasks, appearance, understudy, hooks, lantern, budgets, recipes, review-prompts,
saved-replies, tmux, privacy, plugins, log, about). Panes the server holds ask
their own route and can take a moment. Recipe steps, prompt and reply text, plugin
settings and credentials are never in an answer; names and titles are under
untrusted.
Every answer is one JSON object. ok: true means a window ran the command;
ok: false carries one sentence saying why (no window is open, a change is
off on this server, the setting is not exposed, an argument is outside its set).
Read the sentence and do what it says; do not retry the same call.
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.
- 6d ago First seen · 164 lines · 127 tokens per session scan A 65e99aea4f06
ui-control is a skill published in the GitHub repository SirAllap/agentglass (334 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 2,826 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 2026-10-10.
Other skills, from other repositories
ritual
Discover recurring behaviors from memory and offer to formalize them as scheduled jobs.
overheard
Find commitments the user made in the last two weeks and did not follow through on. A promises audit.
rotator
Rotate to the next connected account with proven headroom when a usage limit hits. Triggers: /rotator, rotate the account, hit my session limit, hit the weekly limit, out of usage, switch account, no headroom left, which account has capacity. Uses the headroom CLI to pick the next eligible login in your configured…
ashlr-lean-tools
Highest-impact token-saving habits for Claude Code tool use. Read-once, batch edits, orient-before-search, skip verification reads, grep-before-read, concise output at high spend. Reduces session token cost 30–60%.
session-recap
Use when the user asks to recap, summarize, or review a Claude Code session — e.g. 'recap my last session', 'what happened in that session', 'session summary'.
standup
Use when the user asks for a standup update, work log, or activity summary — e.g. 'standup update', 'what did I work on today', 'work log', 'daily summary'.