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 skills/sundegan/agent-skills/tauri-codegennpx skills add sundegan/agent-skills --skill tauri-codegengit clone --depth 1 https://github.com/sundegan/agent-skillsWrote 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/sundegan/agent-skills/tauri-codegen)<a href="https://agentmods.dev/skills/sundegan/agent-skills/tauri-codegen"><img src="https://agentmods.dev/badge/skills/sundegan/agent-skills/tauri-codegen.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 | $0.00080 | $0.01847 |
| Opus 5 | $0.00040 | $0.00924 |
| Sonnet 5 | $0.00016 | $0.00369 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
tauri-codegen 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 4d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tauri Codegen
Goal
Implement complete Tauri application changes that fit the existing codebase. Keep code concise, readable, maintainable, and narrowly scoped. Prefer established local patterns over generic Tauri examples, avoid speculative abstractions, remove code made obsolete by the change, and add tests according to behavior and risk.
Workflow
- Establish the task boundary:
- Read the user request and identify the expected behavior, affected platforms, and acceptance criteria.
- Inspect
git status --shortbefore editing. Preserve unrelated user changes. - Locate the Tauri root, frontend root, workspace manifests, package scripts, test setup, and CI checks.
- Discover the local implementation style:
- Determine the Tauri major version from
Cargo.toml, lockfiles, configuration, and existing APIs. Do not assume a version. - Read the closest related Rust modules, frontend components or services, Tauri configuration, capabilities, permissions, and tests.
- Inspect the application shell, global styles, design tokens, shared controls, icons, spacing, typography, window chrome, and nearby screens before changing frontend UI.
- Trace the full path for similar behavior: UI action, frontend wrapper, serialization boundary, Tauri command or event, domain logic, state, and native side effect.
- Record the local conventions for module placement, naming, errors, serialization, state ownership, async work, logging, dependency injection, visual hierarchy, interaction feedback, and tests.
- Determine the Tauri major version from
- Plan the smallest coherent change:
- Reuse existing helpers and boundaries when they fit.
- Add an abstraction only when it removes meaningful duplication, isolates a real boundary, or matches a pattern already used by the repository.
- Avoid generic repositories, service layers, traits, wrappers, builders, or utility modules for a single simple call.
- Keep Tauri commands thin when the codebase already separates transport from domain logic. Otherwise, follow the repository's existing level of separation.
- Implement end to end:
- Make the Rust backend, frontend integration, configuration, permissions, capabilities, and platform-specific changes required for the feature to work.
- Preserve existing public interfaces and behavior unless the task explicitly changes them.
- Make new UI look like part of the existing application and behave like desktop software rather than an embedded website.
- Follow existing error and result types. Return actionable errors across the invoke boundary without exposing sensitive internals.
- Keep payload types explicit and serialization-compatible on both sides.
- Use the repository's established wrappers for
invoke, events, windows, plugins, and native APIs instead of creating parallel access paths.
- Clean up while editing:
- Remove imports, variables, functions, branches, files, feature flags, configuration, permissions, comments, and tests made obsolete by the task.
- Remove task-adjacent dead code only when its obsolescence is clear and removal does not change an unrelated public contract.
- Update all call sites after changing a command, payload, event, state shape, or exported API.
- Do not leave compatibility wrappers, duplicated implementations, or TODO comments unless a real compatibility requirement remains.
- Decide and implement test coverage:
- Inspect nearby tests and CI before choosing the test type.
- Update existing tests whenever the change intentionally alters covered behavior, payloads, errors, snapshots, permissions, or configuration.
- For new features, add unit tests for deterministic Rust domain logic, validation, parsing, state transitions, error mapping, and frontend logic that can run without a desktop runtime.
- Add integration tests when behavior crosses internal modules but can still run without driving the application UI.
- Add end-to-end UI tests when the essential behavior depends on the real Tauri bridge or native application lifecycle, including commands, events, windows, menus, tray actions, dialogs, filesystem access, deep links, or plugin integration.
- Follow the repository's existing UI test framework and fixtures. Do not introduce a new E2E stack when an equivalent one already exists.
- If native automation is unavailable, extract and unit-test deterministic logic, perform the strongest available build or smoke check, and report the untested native path explicitly.
- Avoid tests that only mirror implementation details or assert trivial framework wiring.
- Verify the final result:
- Run the smallest relevant tests first, then the repository's applicable formatter, linter, type checker, Rust checks, and build commands.
- Prefer discovered project commands such as
cargo fmt --check,cargo clippy,cargo test, frontend test scripts, type checks, and Tauri build or dev smoke checks. - For UI changes, inspect the running application at representative window sizes and on each affected platform when available. Check visual consistency, clipping, focus, hover, pressed, disabled, loading, empty, and error states.
- Re-read the final diff for accidental generated files, broad permission changes, duplicated code, stale references, and unrelated formatting churn.
- Confirm that new files are used, removed files are no longer referenced, and the implementation covers the user-visible workflow end to end.
What ships with it
2 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.
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.
- 4d ago First seen · 95 lines · 80 tokens per session scan A 16d7db4a7142
tauri-codegen is a skill published in the GitHub repository sundegan/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,847 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
rust-patterns
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
rust-code-quality
Run a focused Rust quality review when the user requests one, when reviewing a Rust PR/commit, or when another selected review workflow delegates Rust-specific checks. Do not auto-load for every implementation edit.
switchyard-rust-review
Review Switchyard Rust changes for correctness and maintainability. Use for pull requests or diffs touching crates, PyO3 bindings, async runtime behavior, streaming, protocol types, translation, algorithms, or LLM clients.
rust-pro
Master modern Rust (2024 edition) with async patterns, advanced type system features, and production-ready systems programming. Expert in the current Rust ecosystem including Tokio, axum, and modern crates. Use PROACTIVELY for Rust development, performance optimization, or systems programming.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.