Borrowing it
Nothing to install: this file belongs to ItsWendell/palot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ItsWendell/palot/main/.agents/skills/palot-desktop-dev/SKILL.mdgit clone --depth 1 https://github.com/ItsWendell/palotWrote 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/itswendell/palot/palot-desktop-dev)<a href="https://agentmods.dev/skills/itswendell/palot/palot-desktop-dev"><img src="https://agentmods.dev/badge/skills/itswendell/palot/palot-desktop-dev/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/itswendell/palot/palot-desktop-dev"><img src="https://agentmods.dev/badge/skills/itswendell/palot/palot-desktop-dev.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.00873 |
| Opus 5.5 | $0.00028 | $0.00349 |
| Sonnet 5.5 | $0.00014 | $0.00175 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
palot-desktop-dev 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Palot Desktop Development
Keep the OpenCode task host stable while the development client changes.
Choose The Loop
- Use installed Palot Nightly as the host when changing Palot itself.
- In agent worktrees, default to the smallest matching
bun run test:e2e -- <scenario>. Add--visibleonly when the user wants to watch it. - Use
bun run devfor live integration. It connects to the shared user OpenCode service and starts hidden so it does not cover or focus another app. - Use
bun run dev:visiblewhen rendering, interaction, accessibility, screenshots, or visual inspection require a visible native window. It does not take keyboard focus. - Use
bun run dev:focusonly when focus behavior matters or the user explicitly asks for a foreground launch. - Build Nightly and Dev against the exact declared
@opencode/clientversion. Reuse healthy compatible stable 2.x services and reviewed beta services; an unreviewed beta needs exact-version consent. A different patch version is not permission to replace a service. Service replacement can interrupt active turns. - Existing user-installed OpenCode is preferred for confirmed local startup; packaged/app-cached binaries are fallbacks or an explicit user preference. Delegate confirmed package-manager updates to the official CLI, and keep executable updates separate from service restarts. Never update the task host as a side effect of implementing or testing these controls.
Read repository-root ../../../docs/desktop-testing.md before adding an E2E scenario or using real credentials.
Iterate
- Start the supervisor with
bun run devfrom the repository root for background integration. Usebun run dev:visiblewhen the QA evidence requires a visible window, andbun run dev:focusonly for focus-specific behavior or an explicitly requested foreground launch. - Run
bun run dev:infoin that worktree to get its renderer URL, Electron PID, CDP port, and data root. - Let Vite HMR apply renderer-only changes. Let the supervisor restart Electron after main or preload builds.
- After native dependency or generated-binary changes, run
bun run dev:restart -- "reason"as the final tool call. - After supervisor or control-script changes, stop its terminal with Ctrl-C and start it again. A running supervisor cannot replace itself.
What ships with it
1 file 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.
- 1mo ago First seen · 53 lines · 70 tokens per session scan A 983fff17725e
palot-desktop-dev is a skill published in the GitHub repository ItsWendell/palot (194 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 873 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 2026-09-13.
palot-desktop-dev compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| palot-desktop-devItsWendell/palot | Skill | 194 | 2d ago | MIT | A | 70 | Codex |
| repo-readingyknnv/brownspec | Skill | 2 | 2mo ago | MIT | A | 57 | Claude Code |
| check-linkswesammustafa/Claude-Code-Everything-You-Need-to-Know | Skill | 3.5k | 3d ago | none | A | 44 | Claude Code, Codex |
| review-checklistwesammustafa/Claude-Code-Everything-You-Need-to-Know | Skill | 3.5k | 3d ago | none | A | 25 | Claude Code, Codex |
| source-command-methodology-advisorFlorianBruniaux/claude-code-ultimate-guide | Skill | 6.4k | 2d ago | CC-BY-SA-4.0 | A | 27 | Claude Code, Codex |
| methodology-advisorFlorianBruniaux/claude-code-ultimate-guide | Skill | 6.4k | 2d ago | CC-BY-SA-4.0 | A | 25 | Claude Code |
| release-notesFlorianBruniaux/claude-code-ultimate-guide | Skill | 6.4k | 2d ago | CC-BY-SA-4.0 | A | 13 | Claude Code |