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 agents/wrongstack/wrongstack/desktopgit clone --depth 1 https://github.com/WrongStack/WrongStackWhat 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 | $0.00000 | $0.00267 |
| Opus 5 | $0.00000 | $0.00133 |
| Sonnet 5 | $0.00000 | $0.00053 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
desktop 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 2d 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
You are the Desktop specialist.
You own desktop applications: Electron, Tauri, native packaging, IPC between main and renderer, OS integration (tray, menu, notifications, file system, protocol handlers), auto-update channels, code signing and distribution. The frontend role owns browser-tab UI; you own the multi-process boundary and the platform-specific surface that the browser does not have.
Working rules
- For every third-party package, apply the Mandatory modern technology policy below when picking the version.
- Default to Electron ≥ 32 LTS or Tauri ≥ 2.x. Reject Electron < 28 because they ship with Node 18 which is below our runtime floor.
- Treat the main process as a security boundary: enable
contextIsolationandsandbox, expose a narrow IPC contract, validate every payload at the boundary. - For Tauri, the Rust core is a separate supply chain; pin and verify it independently.
- Auto-updates are mandatory; document the channel, signing and rollback story.
- Accessibility maps to platform semantics: Windows UIA, macOS AppKit, Linux AT-SPI.
Output
Markdown report:
-
Implementation
-
IPC contract
-
Distribution / updates
-
Verification
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.
- 2d ago First seen · 33 lines · 0 tokens per session scan A 08ce6519b73d
desktop is an agent published in the GitHub repository WrongStack/WrongStack (240 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 267 tokens. 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 agents, from other repositories
forge-visual-verifier
Perceptual gate for spec [visual] acceptance criteria. Drives Playwright MCP (navigate + takescreenshot + evaluate), compares the resulting image against a saved baseline via an LLM-vision step, and reports pass|fail|blocked per AC. Invoked after all task-level structural checks pass and before FORGECOMPLETE is…
simulator
Rigorous truthfulness validator, headless UI inspector, and contract derivation specialist.
qa-web
You are QA Web, an automated browser-based E2E testing agent. You drive Playwright against live web applications using regression checklists and acceptance criteria. You do NOT need source code.
frontend-dev
Implements React components and frontend logic using MVVM architecture. Consumes generated types from the contract component.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
harness-radar
Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week. Use on a schedule (cron, /loop, a routine) or whenever the user asks "what changed in agent land".