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/devlint/gitwand/add-tauri-commandnpx skills add devlint/GitWand --skill add-tauri-commandgit clone --depth 1 https://github.com/devlint/GitWandWhat 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 | $0.00050 | $0.01581 |
| Opus 5 | $0.00025 | $0.00790 |
| Sonnet 5 | $0.00010 | $0.00316 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
add-tauri-command 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 yesterday.
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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill : add-tauri-command
Ajouter une commande Tauri de bout en bout — Rust + TypeScript dans le même commit, sans trou de sécurité.
Les deux fichiers cibles sont toujours :
apps/desktop/src-tauri/src/lib.rs— implémentation Rustapps/desktop/src/utils/backend.ts— wrapper TypeScript
Les composants et composables Vue ne doivent jamais appeler invoke() directement. Tout passe par backend.ts.
Étape 1 — Spécifier la commande
Avant d'écrire une ligne de code, répondre à ces questions :
| Question | Impact |
|---|---|
| Nom de la commande ? | snake_case en Rust, camelCase en TS |
| Paramètres et leurs types ? | Identifier ceux qui sont des chemins → safe_repo_path obligatoire |
| Type de retour ? | Définir / réutiliser une interface TS dans types.ts |
| Spawne-t-elle un process externe ? | Vérifier les capabilities Tauri |
Exécute-t-elle git ? |
Règle .arg() obligatoire, jamais format!() |
Étape 2 — Implémenter en Rust dans lib.rs
Appliquer les règles dans cet ordre exact :
2a. Tout paramètre chemin passe par safe_repo_path()
/// Retourne le contenu du fichier de config d'un repo.
#[tauri::command]
fn read_config_file(cwd: String, path: String) -> Result<String, String> {
// ✅ TOUJOURS : valider le chemin avant tout usage
let safe = safe_repo_path(&cwd, &path)
.map_err(|e| e.to_string())?;
let content = std::fs::read_to_string(&safe)
.map_err(|e| e.to_string())?;
Ok(content)
}
// ❌ JAMAIS : path traversal possible
fn read_config_file(cwd: String, path: String) -> Result<String, String> {
let full = std::path::PathBuf::from(&cwd).join(&path); // "../../../etc/passwd" passe !
Ok(std::fs::read_to_string(full).map_err(|e| e.to_string())?)
}
2b. Les commandes git utilisent .arg() séparé — jamais format!()
// ✅ Chaque argument est isolé : pas d'injection possible
let output = Command::new(git_binary())
.arg("log")
.arg("--oneline")
.arg("-n").arg(&limit.to_string())
.arg("--").arg(&safe_path)
.current_dir(&cwd)
.output()
.map_err(|e| e.to_string())?;
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.
- yesterday First seen · 191 lines · 50 tokens per session scan A 3174f487230b
add-tauri-command is a skill published in the GitHub repository devlint/GitWand (167 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 1,581 once invoked, about $0.0003 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
hunk-extensions
Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-review
Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
mobile-app
像素级 iPhone 15 Pro 边框, 一屏 app 截图.
git-machete
Use whenever invoking the git machete CLI to organize branch chains, compute fork points, run stacked rebases/merges, or manage GitHub/GitLab PR/MR chains - especially in a repo that already has a .git/machete file. Lists which subcommands modify .git/machete, run rebase/merge, run hooks, or read stdin, so the agent…