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/rakutentech/sorify/gatewaygit clone --depth 1 https://github.com/rakutentech/sorifyWhat 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 | $0.00117 | $0.04875 |
| Opus 5 | $0.00059 | $0.02438 |
| Sonnet 5 | $0.00023 | $0.00975 |
| Haiku 4.5 | $0.00012 | $0.00487 |
Grade A, and why
gateway 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.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sorify:gateway
Trigger
Invoked as /sorify:gateway {question}. The question may be empty (show full
overview), about how the plugin works, about a specific MCP tool, or a
request for live data from Sorify.
Step 1: Classify the input
empty / "help" / "overview" / "how does this work"
→ Full Overview (Step 2)
mentions a specific tool name, or "what tools", "what can I do with X"
→ Tool Reference (Step 3), scoped to the matching section if one is named
asks for live data: "list suites", "show suite {id}", "what tests are in
suite {id}", "list runs", "status of run {id}", "screenshots for result {id}"
→ Live Lookup (Step 4)
If the request is ambiguous, do the closest of these three rather than asking a clarifying question — this is a read-only help command, so a wrong guess costs nothing.
Step 2: Full Overview
Output this, filling in SORIFY_BASE_URL from ~/.sorify if present:
=== Sorify Plugin ===
Sorify is a Claude Code plugin that generates Playwright E2E tests from a
URL (optionally cross-referenced with source code), uploads them to a
Sorify TestSuite, runs them, and reports pass/fail.
It talks to the Sorify web app over MCP — every action available on the
Sorify dashboard (suites, tests, runs, screenshots) is also callable
as an MCP tool by Claude directly, without the dashboard UI.
Commands
──────────────────────────────────────────────
/sorify:generate {url} [source] Generate + upload + run tests for a URL
/sorify:gateway [question] This command — docs + live MCP lookups
Setup (~/.sorify)
──────────────────────────────────────────────
SORIFY_URL=https://your-sorify-host/sorify
[email protected]
SORIFY_PASSWORD=your-password
SORIFY_URL must be a real shell env var (source ~/.sorify with `set -a` in
your shell profile) so the MCP client can build the server URL from it.
USERNAME/PASSWORD are read directly by a helper script to build the
request's Basic-Auth header — they don't need to be exported.
These three values are MCP-connection credentials only — they authenticate the
plugin's MCP client to the Sorify server. They are PRIVATE and must never be
copied into, echoed as, or used as a suite variable `value` (suite variables are
for target-webpage test accounts — see "Suite variables" below).
MCP Server
──────────────────────────────────────────────
Name: Sorify (registered in this plugin's .mcp.json as "sorify")
Purpose: Manage Sorify test suites, tests, runs, and screenshots
Tools: 34 total across 4 resource groups — run `/sorify:gateway tools` for
the full reference, or `/sorify:gateway {topic}` for one group
(suites / tests / runs / screenshots)
Dashboard: {SORIFY_BASE_URL}
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 · 264 lines · 117 tokens per session scan A c3cd51c1044c
gateway is a command published in the GitHub repository rakutentech/sorify (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 117 tokens to every session and 4,875 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other commands, from other repositories
record
Record the browser while validating a flow, then judge it against a rubric.
mbt
Run a browser automation task on a website in natural language (alias for /muggle-browser-task).
mdo
Muggle AI autonomous workflow entry point (alias for /muggle-do).
mfeedback
Submit, list, or delete Muggle Test feedback (alias for /muggle-feedback).
mimport
Import existing tests/PRDs/specs INTO Muggle Test (alias for /muggle-test-import).
mpr
Post the Muggle E2E visual walkthrough to a PR (alias for /muggle-pr-visual-walkthrough).