HuLa is a cross-platform instant messaging application for desktop and mobile devices, built with Rust, Vue, TypeScript, Tauri, and Vite. It is intended for users who need private chats, group conversations, authentication, and related messaging features across Windows, macOS, Linux, Android, and iOS.
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 HuLaSpark/HuLa --skill hula-skillgit clone --depth 1 https://github.com/HuLaSpark/HuLaWrote 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/hulaspark/hula/hula-skill)<a href="https://agentmods.dev/skills/hulaspark/hula/hula-skill"><img src="https://agentmods.dev/badge/skills/hulaspark/hula/hula-skill/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/hulaspark/hula/hula-skill"><img src="https://agentmods.dev/badge/skills/hulaspark/hula/hula-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.00427 |
| Opus 5.5 | $0.00034 | $0.00171 |
| Sonnet 5.5 | $0.00017 | $0.00085 |
| Haiku 4.5 | $0.00009 | $0.00043 |
Grade A, and why
hula-skill 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 1mo 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.
What it actually says
HuLa Skill
Overview
Enable consistent changes across the HuLa frontend, backend, full-stack flows, and build/release tasks with repo-specific conventions and resources.
Activation Gate
Ask which scope to enable: frontend, backend, fullstack, or build-release. Confirm platform (desktop or mobile), target area (view/component/store/command), and any constraints before editing.
Workflow
- Identify scope and platform.
- Locate similar code paths and follow existing patterns.
- Apply changes using repo conventions and available templates.
- Update related layers (routes, stores, commands) when needed.
- Propose or run checks/tests only when requested.
Scope Routing
- Frontend: read
references/frontend.mdandreferences/overview.md; useassets/templates/view-desktop.vue,assets/templates/view-mobile.vue,assets/templates/pinia-store.tsas starters. - Backend: read
references/backend.mdandreferences/overview.md; useassets/templates/tauri-command.rs. - Fullstack: read
references/fullstack.mdplus frontend/backend references; useassets/templates/tauri-command.ts. - Build/Release: read
references/build-release.mdandreferences/checklists.md.
Scripts
Use scripts/hula_summary.py for quick repo context (views/stores counts and paths).
Use scripts/hula_tauri_map.py to list Tauri commands and frontend invoke usage.
References
Use references/overview.md for stack, directories, aliases, and global conventions.
Use references/checklists.md for per-scope checklists.
What ships with it
13 files 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.
- assets/templates/pinia-store.ts 352 B runs code
- assets/templates/tauri-command.rs 110 B
- assets/templates/tauri-command.ts 346 B runs code
- assets/templates/view-desktop.vue 355 B
- assets/templates/view-mobile.vue 311 B
- references/backend.md 764 B
- references/build-release.md 477 B
- references/checklists.md 1023 B
- references/frontend.md 1.2 KB
- references/fullstack.md 779 B
- references/overview.md 1.3 KB
- scripts/hula_summary.py 2.1 KB runs code
- scripts/hula_tauri_map.py 3.8 KB runs code
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.
- 1mo ago First seen · 41 lines · 86 tokens per session scan A 169b5d0b741f
hula-skill is a skill published in the GitHub repository HuLaSpark/HuLa (7,771 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 427 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
skill-deployment
Use when deploying the shared agent skills via chezmoi, or fixing "not managed" errors.
hermes-cron-automations
Use when building a recurring automation on the Hermes box.
github-pr-workflow
GitHub issues and PR lifecycle: file/triage issues, carry an issue to a verified PR, branch, commit, open, CI, merge.
cross-os-test-coverage
Use when adding or auditing test coverage for another OS.
debugging-hermes-tui-commands
Debug Hermes TUI slash commands: Python, gateway, Ink UI.
github-actions-trigger-gotchas
Use when GitHub Actions triggers fire wrong or not at all.