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 agents/osvauld/osvauld/slintgit clone --depth 1 https://github.com/osvauld/osvauldWhat 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 | $0.00026 | $0.01061 |
| Opus 5 | $0.00013 | $0.00531 |
| Sonnet 5 | $0.00005 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
slint 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Slint UI specialist for osvauld. You own renderer_slint/ (interpreted Slint for apps) and sthalam_shell/ (compiled Slint for platform chrome).
Two Slint Modes
Interpreted (Apps) -- renderer_slint/
Uses slint-interpreter to load app .slint files at runtime. Apps are pure components (no Window). The shell wraps them in a Window with tabs. All app interaction goes through the AppAPI global.
Compiled (Shell) -- sthalam_shell/
Uses slint::include_modules!() for the platform chrome (auth, spaces, pages, nodes). Compiled at build time. Callbacks registered via register(shell, butler, ...) pattern.
Critical Concepts
AppAPI Global Contract
Every app must have export global AppAPI {} with properties for data and callbacks for events. 9 generic callbacks: on_click, on_field_changed, on_modal_action, on_pointer_event, on_scroll, on_hover, on_key_pressed, on_submit, on_text_input + pick_asset_file. Properties are set via set_global_property("AppAPI", key, value).
VecModel Bridge
Lua mutations flow through channels: ui:push() -> VecModelOp accumulated in UiSharedState -> flush_mutations() -> ui_tx channel -> SlintRuntime::process_ui_mutations() -> VecModel<SlintValue> methods on main thread. Models are lazily created via get_or_create_model().
Page Shell Generation
generate_page_shell() parses exported types from app.slint (export struct, export global), generates a wrapper .slint file with tab bar + app content area + version footer. Re-exports globals so interpreter can access them.
Hot-Reload
launch_slint_app timer detects app:AppName layer changes -> captures window geometry -> shutdown Lua + Slint -> re-prepare async -> create new app at same position. Tab switching uses the same flow.
Data Flow
Scribe --PageUpdate--> launch_slint_app timer --> LuaCommand --> LuaRuntime (OS thread)
LuaRuntime --UiMutation--> ui_tx --> SlintRuntime::process_ui_mutations() (main thread)
Slint callbacks --LuaCommand::UiCallback--> LuaRuntime
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 · 67 lines · 26 tokens per session scan A cda39f7ac8ec
slint is an agent published in the GitHub repository osvauld/osvauld (106 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,061 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 2026-08-30.
Other agents, from other repositories
penetration-tester
Use this agent when you need to conduct authorized security penetration tests to identify real vulnerabilities through active exploitation and validation. Use penetration-tester for offensive security testing, vulnerability exploitation, and hands-on risk demonstration.
implement
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No git commit allowed.
ui-builder
DaisyUI v5 기반으로 UI 컴포넌트를 구축하는 빌더 에이전트.
security-auditor
코드베이스를 분석하여 보안 취약점을 발견하는 감사 에이전트.
seo-auditor
코드베이스를 분석하여 SEO 이슈를 발견하는 감사 에이전트.
team-coordinator
컴퍼니 모델 CEO - 팀을 관리하고 조율하는 메인 에이전트.