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 hecatehq/hecate --skill taurigit clone --depth 1 https://github.com/hecatehq/hecateWrote 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/hecatehq/hecate/tauri)<a href="https://agentmods.dev/skills/hecatehq/hecate/tauri"><img src="https://agentmods.dev/badge/skills/hecatehq/hecate/tauri.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.10183 |
| Opus 5 | $0.00024 | $0.05091 |
| Sonnet 5 | $0.00010 | $0.02037 |
| Haiku 4.5 | $0.00005 | $0.01018 |
Grade A, and why
hecate-tauri 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 7d 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 — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hecate Tauri skill
Use this skill for any work inside tauri/. Gateway changes use ../backend/SKILL.md; UI changes use ../ui/SKILL.md.
Operator-facing companion: ../../../docs/operator/desktop-app.md — distribution, current state, roadmap, footguns. When this skill grows a footgun an end user might hit, mirror it there.
Canonical guidance lives here
../../core/project-context.md— repo layout, toolchain pins, storage tiers.../../core/engineering-standards.md— cross-project conventions.../../core/workflow.md— operating loop, commit etiquette.../../core/verification.md— verification ladders and done criteria.
Architecture in one paragraph
The Tauri app is a thin chrome-frame around the main Hecate runtime running in gateway mode. On launch the Rust layer allocates a free loopback port, spawns the hecate binary as a companion process (not a Tauri shell-plugin sidecar — see gotchas), polls /healthz until the gateway is healthy, then navigates the webview to http://127.0.0.1:{port}/. The gateway serves its own embedded React UI. No second frontend build, no API bridge, no Vite dev server required.
Why we keep //go:embed instead of frontendDist
Most Tauri apps point tauri.conf.json → frontendDist: "../ui/dist" and let the webview load UI files directly from the bundled app. We don't, on purpose:
- Same-origin loopback surface. The webview loads from
http://127.0.0.1:{port}/and the API is athttp://127.0.0.1:{port}/v1/.... Same origin means no CORS dance and no Tauri IPC bridge. Splitting UI (tauri://localhost) from API (127.0.0.1:{port}) breaks that property and requires a meaningful security refactor to restore. - Hecate-sidecar property. The same
hecateruntime binary ships through Docker, the goreleaser tarballs, and the Tauri sidecar. The embed makes that work without conditional builds or runtime path resolution. Readingui/distfrom disk inside a bundled.appwould require a working-dir-independent resolver and a new "UI files missing" failure mode. - Bundle-size cost is negligible. The built UI is ~730 KB on disk (~200 KB gzipped over the wire). Embedding it adds ~2% to the
hecatebinary (32 MB → 33 MB) and ~1 MB to the.dmg. Desktop apps routinely ship at 100+ MB; this isn't even close to a constraint, and any "ship a UI-less variant" optimization would save kilobytes for a meaningful maintenance cost.
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.
- 7d ago First seen · 469 lines · 49 tokens per session scan A f4b30545bc91
hecate-tauri is a skill published in the GitHub repository hecatehq/hecate (22 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 10,183 once invoked, about $0.0002 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 skills, from other repositories
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
self-host-studio
Install and self-host deco Studio (the open-source control plane) on the user's own infrastructure. Use when the user wants to install, run, self-host, or deploy Studio locally (Docker, Rancher Desktop, kind, minikube) or on Kubernetes (managed or self-managed), or asks to "install Studio", "self-host decocms"…
slides
Create and edit presentation decks as single self-contained HTML files with a live, editable preview and print-to-PDF export. Use when the user wants slides, a deck, or a presentation.
brand
Create and maintain an org's brand as a folder the whole platform reads: colors, type, voice, logo and a deck theme. Use this whenever someone asks to "set up our brand", "make a brand kit", "apply our colors/fonts", or before producing branded artifacts (decks, pages, emails). One brand = one folder; everything that…
decocms-ui
Build or style React UI with the decocms product design system (@decocms/ui). Use when creating interfaces, pages, or components in a project that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers installation…
templating
Render any text file (HTML, markdown, config, SQL, email) from a mustache template plus JSON data. Use when an output's shape is fixed ahead of time and only the values change.