verify

A command for visually checking a screen or feature without running the complete workflow. It can use Maestro for mobile apps and Playwright for websites.

In plain words
What is it for?
For standalone visual checks of mobile or web features in an initialized SoloFlow project.
Why use it?
It makes it possible to inspect one interface change directly instead of running unrelated workflow steps first.

Command

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 commands/kesteva/soloflow/verify
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,335 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 $0.00023 $0.01335
Opus 5 $0.00012 $0.00668
Sonnet 5 $0.00005 $0.00267
Haiku 4.5 $0.00002 $0.00134

Measured 2d ago against content hash b5e7b0cab7fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

verify 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

2. **Probe CLI.** Run `which maestro` via Bash. If not found AND MCP probe failed, report: "Maestro is not available via MCP or CLI. Install the CLI with: `curl -Ls 'https://get.maestro.mobile.dev' | bash`, or register t

Makes network callslowCapability

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

2. **Probe CLI.** Run `which maestro` via Bash. If not found AND MCP probe failed, report: "Maestro is not available via MCP or CLI. Install the CLI with: `curl -Ls 'https://get.maestro.mobile.dev' | bash`, or register t
commands/verify.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soloflow:verify

You are running standalone visual verification. The user wants to visually check a screen or feature without running the full workflow.

The target to verify is: $ARGUMENTS

Step 0: Check initialization

If .soloflow/ does not exist, report: "SoloFlow not initialized. Run /soloflow:init first." and stop.

Step 1: Check Availability

Pick a mobile path once per the Path Selection recipe in skills/visual-verify/SKILL.md, then probe web.

For mobile verification (MCP preferred, CLI fallback):

  1. Probe MCP. Call mcp__maestro__list_devices. If it returns a result, set USE_MAESTRO_MCP=true. If the tool is unbound or the call errors, continue.
  2. Probe CLI. Run which maestro via Bash. If not found AND MCP probe failed, report: "Maestro is not available via MCP or CLI. Install the CLI with: curl -Ls 'https://get.maestro.mobile.dev' | bash, or register the MCP server with: claude mcp add --scope user maestro maestro mcp."
  3. Probe device. Regardless of path, at least one simulator/emulator must be booted:
    IOS=$(xcrun simctl list devices booted 2>/dev/null | grep -c Booted || true)
    AND=$(adb devices 2>/dev/null | awk '$2=="device"' | wc -l | tr -d ' ' || true)
    
    If both are zero, report: "No simulator/emulator booted. Start one with: open -a Simulator (iOS) or emulator -avd <name> (Android)." (MCP's start_device can also boot one for you if you prefer — but the user likely wants an explicit choice.)

For web verification:

  1. Run which npx via Bash.
  2. If not found, report: "npx is not available. Ensure Node.js is installed."
  3. If found, attempt a Playwright MCP probe. If the MCP server is not running, report: "Playwright MCP server is not available. Ensure Playwright MCP is configured in your settings."

If neither mobile nor web tooling is available, report this to the user and stop.

Step 2: Discover Context

  1. Search the codebase for files related to the user's target (use Grep/Glob)
  2. Search for existing Maestro flows in maestro/, .maestro/, test/maestro/ that match the target
  3. Determine whether this is a mobile UI, web UI, or both

Read the full file on GitHub · 97 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 · 97 lines · 23 tokens per session scan C b5e7b0cab7fe

Subscribe to this mod's changes

verify is a command published in the GitHub repository kesteva/soloflow (41 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,335 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.