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/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/memory-optimization)<a href="https://agentmods.dev/plugins/yeaight7/agent-powerups/memory-optimization"><img src="https://agentmods.dev/badge/plugins/yeaight7/agent-powerups/memory-optimization/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/yeaight7/agent-powerups/memory-optimization"><img src="https://agentmods.dev/badge/plugins/yeaight7/agent-powerups/memory-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
memory-optimization 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 yesterday.
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": "memory-optimization",
"version": "0.6.3",
"description": "Graph-backed memory and context optimization workflows with graphify first and document conversion helpers second.",
"author": {
"name": "yeaight7"
},
"homepage": "https://github.com/yeaight7/agent-powerups#readme",
"repository": "https://github.com/yeaight7/agent-powerups",
"license": "Apache-2.0",
"keywords": [
"graphify",
"memory",
"optimization",
"markdown",
"obsidian"
],
"maturity": "beta"
}
What it installs
The manifest is a name and a version. 6 skills, 3 commands, 2 agents travel with it, and installing the plugin installs all of them — 390 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill memory-build-workflow A 39 tokens
- Skill memory-optimization-workflow A 39 tokens
- Skill markitdown-file-intake A 37 tokens
- Skill memory-query-workflow A 33 tokens
- Skill defuddle A 29 tokens
- Skill graphify A 61 tokens
- Command memory-build A 27 tokens
- Command memory-optimize A 26 tokens
- Command memory-query A 25 tokens
- Agent memory-optimizer A 37 tokens
- Agent graph-memory-curator A 37 tokens
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.
- yesterday First seen · 20 lines scan A 3df9762e6b32
memory-optimization is a plugin published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 2d 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 2026-09-14.
Other plugins, from other repositories
imprint
Your habits, imprinted on AI, plus judgment that adapts to you: when to act, when to check first, when the project rules win. A portable working profile across every agent. Powered by I-Lang v5.0.
imprint
Your habits, imprinted on AI. One extension replaces eleven skills: memory, compression, onboarding, code review, debugging, planning, progress tracking, testing, git workflow, SEO, and copywriting.
tokenless
Tokenless context compression for Claude Code. Cap noisy tool output locally before it enters model context.
agent-antigravity
MCP server + skill for Google Gemini Antigravity agent: sandbox code execution, web search, GitHub clone-branch-PR workflow, cron triggers.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.