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/RayFernando1337/rayfernando-skillsWrote 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/plugins/rayfernando1337/rayfernando-skills/waves)<a href="https://agentmods.dev/plugins/rayfernando1337/rayfernando-skills/waves"><img src="https://agentmods.dev/badge/plugins/rayfernando1337/rayfernando-skills/waves/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/plugins/rayfernando1337/rayfernando-skills/waves"><img src="https://agentmods.dev/badge/plugins/rayfernando1337/rayfernando-skills/waves.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
waves 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 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.
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.
What it actually says
{"name":"waves","version":"0.6.0","description":"WAVES (Workers, Aggregate, Verify, Extend): wave-based orchestration for Cursor. Decompose a big task into independent slices, fan them out to isolated parallel subagents with the Task tool as a bounded wave, verify each handoff, then synthesize. The manifest is the stop function: continue until every slice is terminal; stop only on completion, stagnation, or budget. Reduce entropy first; route scouting to cheap fast models. Runs in place of cloud orchestration. Opt-in via /waves. Formerly parallel-orchestrate.","author":{"name":"Ray Fernando","url":"https://github.com/RayFernando1337"},"homepage":"https://github.com/RayFernando1337/rayfernando-skills","repository":"https://github.com/RayFernando1337/rayfernando-skills","license":"Apache-2.0","keywords":["waves","wave-engineering","orchestration","parallel","subagents","multitask","fan-out","cursor","task-tool","research","audit","verification","handoffs","entropy-reduction","decomposition","model-routing","composer","parallel-orchestrate","evals"]}What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 126 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 1 lines scan A 1829886960a8
waves is a plugin published in the GitHub repository RayFernando1337/rayfernando-skills (129 stars, last pushed 2mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
pm-superpowers
Product strategy skills for PMs: find-your-moat front door, 6-step strategy framework, competitive landscape analysis, VRIO, strategic moats, product ecosystem strategy, pre-mortem risk analysis, AI prompt builder, verification, stakeholder alignment, decision log, and prioritization.
hermes-tweet
Documentation-only PM workflows for X/Twitter research through a separate Hermes Tweet runtime.
helius
Build on Solana with Helius — live blockchain tools, expert coding patterns, and autonomous account signup.
propose
Design workflow in the RFC tradition: problem -> alternatives -> tradeoffs -> design -> risks -> recommendation -> impl plan. Two sizes with hard ceilings. Forces reasoning before action. Optional GitNexus + Exa integration.
review
Deep code review driven by a short interview: read-only reader agents per angle, verified findings, and each point routed to ship, issue, brief or propose.
the-loop
An opinionated product-development-lifecycle harness that lets coding agents deliver work items end-to-end, with minimal human intervention, through a predictable loop of plan, execute, self-review, critic-review and escalate.