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 commands/kesteva/soloflow/visual-smokegit clone --depth 1 https://github.com/kesteva/soloflowWhat 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 | $0.00021 | $0.02281 |
| Opus 5 | $0.00010 | $0.01141 |
| Sonnet 5 | $0.00004 | $0.00456 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade C, and why
visual-smoke 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 3d 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.
> Maestro not available. 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`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> Maestro not available. 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`. How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/soloflow:visual-smoke
Diagnostic command that exercises the visual-verification stack end-to-end
to confirm both Maestro (mobile) and Playwright (web) are wired up
correctly. Unlike /soloflow:verify, this is not about checking a
specific feature — it answers the prior question: is my visual-verification
environment actually working before I trust it for real verification runs?
The command is fully automated, requires no arguments, and does not
depend on .soloflow/ being initialized. It can run on a fresh machine to
diagnose setup issues.
Per-platform result is one of:
PASS— every probe succeeded; visual verification works on this platform.SKIP— platform tooling intentionally absent (e.g., no Playwright MCP registered, no simulator booted). Reported with the exact remediation.FAIL— tooling is present but a probe errored mid-run. Reported with the failing step and error text.
Always run BOTH platforms (or attempt to). Never short-circuit one because the other passed/failed.
Step 1: Maestro path probe
Pick a single mobile path up front. Mixing MCP and CLI in one run causes
port-7001 contention (see skills/visual-verify/SKILL.md for the rule).
- MCP probe. Call
mcp__maestro__list_devices. If it returns a result without erroring, setMAESTRO_PATH = "mcp"and capture the device list. - CLI probe (only if MCP failed). Run
which maestrovia Bash. If a path is returned, setMAESTRO_PATH = "cli". Otherwise setMAESTRO_PATH = "none".
If MAESTRO_PATH = "none": emit mobile_result = SKIP with the message:
Maestro not available. Install the CLI with
curl -Ls https://get.maestro.mobile.dev | bash, or register the MCP server withclaude mcp add --scope user maestro maestro mcp.
Skip to Step 4 (Playwright). Do not abort the command.
Step 2: Maestro device probe
Confirm at least one simulator or emulator is booted. Run via Bash:
IOS=$(xcrun simctl list devices booted 2>/dev/null | grep -c Booted || true)
AND=$(adb devices 2>/dev/null | awk '$2=="device"' | wc -l | tr -d ' ' || true)
echo "ios_booted=$IOS android_attached=$AND"
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.
- 3d ago First seen · 217 lines · 21 tokens per session scan C 28efc942846a
visual-smoke is a command published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 2,281 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.