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/boykush/scrapsWrote 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/boykush/scraps/pkm)<a href="https://agentmods.dev/plugins/boykush/scraps/pkm"><img src="https://agentmods.dev/badge/plugins/boykush/scraps/pkm/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/boykush/scraps/pkm"><img src="https://agentmods.dev/badge/plugins/boykush/scraps/pkm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pkm 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.
What it actually says
{
"name": "pkm",
"version": "0.3.1",
"description": "Personal knowledge management skills for a Scraps wiki - learn a source through explanation and comprehension checks and record only what was understood, or digest an article or talk into a short linked summary without dialogue.",
"author": {
"name": "boykush",
"email": "[email protected]"
},
"homepage": "https://boykush.github.io/scraps",
"repository": "https://github.com/boykush/scraps"
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 253 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.
- 2d ago Changed cfc7b82cecca
- 3d ago Changed 9d072309805e
- 4d ago Changed f07bdb6ce1be
- 5d ago First seen · 12 lines scan A a1d88349ad06
pkm is a plugin published in the GitHub repository boykush/scraps (45 stars, last pushed today), licensed MIT. 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 2026-10-11.
Other plugins, from other repositories
better-fullstack
Let your AI assistant scaffold and extend Better Fullstack projects through the official MCP server and focused skills.
claudectl
Hive mind for Claude Code that learns from you once and remembers everywhere — local LLM brain, session monitoring, spend control.
kipi-core
Core founder OS — voice, research, AUDHD, LinkedIn/brand, RCA skills + kipi-mcp server.
prd-os
PRD operating system: capture rough ideas, draft reviewable PRDs, run standard and adversarial review (Codex or a Claude senior-staff-engineer subagent, recorded truthfully), triage findings, decompose approved PRDs into atomic issue specs, and execute those issues with scope enforcement, stop-gate receipts, and…
kipi-ops
GTM and council skills.
logs-locally-plugin
Store and browse AI agent session logs locally with a SQLite database and web UI.