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.
git clone --depth 1 https://github.com/surajpratap/claude-wow-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/surajpratap/claude-wow-plugin/tester)<a href="https://agentmods.dev/commands/surajpratap/claude-wow-plugin/tester"><img src="https://agentmods.dev/badge/commands/surajpratap/claude-wow-plugin/tester/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/surajpratap/claude-wow-plugin/tester"><img src="https://agentmods.dev/badge/commands/surajpratap/claude-wow-plugin/tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.06206 |
| Opus 5.5 | $0.00011 | $0.02482 |
| Sonnet 5.5 | $0.00005 | $0.01241 |
| Haiku 4.5 | $0.00003 | $0.00621 |
Grade C, and why
tester 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 1mo 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.
{"step": 1, "do": "rm -rf bridge/slack/dist && /reload-plugins && /claude-wow:slacker reset", "expect": "hello payload contains 'healthy'; no 'spawn-fail' / 'npm run build failed' / 'dist missing' status"}, Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
You write test-stories and bug reports. You exercise the running product — browser flows via the **official Playwright MCP server** (the `playwright` plugin is a hard dependency of `claude-wow`, so the tools are prefixed The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 1mo ago First seen · 243 lines · 27 tokens per session scan C 9f9841f0a87f
tester is a command published in the GitHub repository surajpratap/claude-wow-plugin (4 stars, last pushed 1mo ago), with no licence file. It adds 27 tokens to every session and 6,206 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
mpr
Post the Muggle E2E visual walkthrough to a PR (alias for /muggle-pr-visual-walkthrough).
explore-release
This legacy command is a rename notice only. Its workflow is now rpi-explore-release.
README
Command "README" from hiromaily/go-crypto-wallet, covering claude code commands, commands, btc e2e commands, workflow and related.
merge-and-test
You are an AI assistant that reads a merge plan from a GitHub issue or markdown file, processes each PR in order (checkout, merge, run Chrome DevTools MCP tests), and creates a "Manual Testing" issue for scenarios that cannot be automated.
playwright-test-heal
Run all my tests and fix the failing ones.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.