verifier-gui

A guide for controlling the Silo desktop app through a development automation bridge and collecting runtime evidence such as screenshots and page details.

In plain words
What is it for?
Creating and deleting test workspaces, opening terminals and files, running commands, inspecting the interface, and capturing screenshots during verification.
Why use it?
It provides a repeatable way to test changes in a safe temporary workspace without altering the user's real workspaces or terminals.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/silo-code/silo/verifier-gui
Any agent
npx skills add silo-code/silo --skill verifier-gui
Clone the repo
git clone --depth 1 https://github.com/silo-code/silo

Made for: Claude Code, Codex.

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,573 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00097 $0.04573
Opus 5 $0.00048 $0.02286
Sonnet 5 $0.00019 $0.00915
Haiku 4.5 $0.00010 $0.00457

Measured 2d ago against content hash 8865ae751fb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

verifier-gui scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$WS_DIR"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`Bash` call.** The `silo()` helper is just `curl`; bash variables (`WS_ID`,
.agents/skills/verifier-gui/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Silo GUI Verifier

The handle the verify skill looks for: how to get the running Silo app under control and capture evidence from it. Silo is a Tauri desktop app; its surface is pixels + a dev-only RPC bridge. This skill drives that bridge.

It does not judge. It launches, drives, captures. The verdict is verify's.

Golden rule 1: verify in a sandbox workspace, never the user's

The app may be the user's live session with real workspaces and terminals. Do all verification in a workspace you create from a temp dir, and delete it when done. Never openTerminal/deleteWorkspace/openFile against an existing workspace — you'd pollute or destroy real state. Create → activate → verify → delete. This also makes destructive paths (workspace delete, session kill) safe to exercise.

Golden rule 2: one turn, not one op per turn

The wall-clock cost here is agent turns, not the RPC bridge — each bridge call is ~milliseconds on localhost, but every separate Bash tool call is a full model round-trip (seconds). So issue a whole drive + capture sequence as a single Bash call. The silo() helper is just curl; bash variables (WS_ID, WS_DIR) persist within one invocation, so create → activate → drive → screenshot → decode all belong in one block (see §2). A 6-step flow then costs 2 turns, not 7.

Only split into a separate turn when you genuinely must:

  • The final Read /tmp/silo.pngRead is its own tool, so capture-in-one-turn then read-in-the-next is the floor (2 turns).
  • Branching on an observed result — if the next op depends on what you saw (a count, a tab list, a pass/fail), end the block, read the output, then decide. A fixed setup sequence has no such dependency — never split it.

Echo any state you'll need next turn (e.g. echo "WS_ID=$WS_ID") — bash vars die at the end of the Bash call.

1. Get the app up (attach or launch)

The bridge listens on 127.0.0.1:7878 (dev builds only — app:dev is built --features automation). Define the request helper first — the contract is strict: header X-Silo-Automation: 1 and a loopback Host, POST /, body {"op", "args"}.

Read the full file on GitHub · 305 lines

Changes

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.

  1. 2d ago First seen · 305 lines · 97 tokens per session scan C 8865ae751fb5

Subscribe to this mod's changes

verifier-gui is a skill published in the GitHub repository silo-code/silo (53 stars, last pushed 2d ago), licensed MIT. It adds 97 tokens to every session and 4,573 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.