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/sukoji/loadoutWrote 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/sukoji/loadout/loadout)<a href="https://agentmods.dev/plugins/sukoji/loadout/loadout"><img src="https://agentmods.dev/badge/plugins/sukoji/loadout/loadout/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/sukoji/loadout/loadout"><img src="https://agentmods.dev/badge/plugins/sukoji/loadout/loadout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
loadout 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "loadout",
"displayName": "Loadout",
"version": "0.5.2",
"description": "Profile a software project and recommend a focused loadout of MCP servers, hooks, and skills for the active coding agent.",
"author": {
"name": "sukoji"
},
"homepage": "https://github.com/sukoji/loadout",
"repository": "https://github.com/sukoji/loadout",
"license": "MIT",
"keywords": ["setup", "recommender", "mcp", "skills", "hooks", "onboarding", "curated"]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 94 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 · 15 lines scan A c89a03935e14
loadout is a plugin published in the GitHub repository sukoji/loadout (3 stars, last pushed 5d ago), 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 2026-08-31.
Other plugins, from other repositories
skillci
Lint, eval, and regression-test Claude Skills against a model matrix. Installs skillci-guardrails, which auto-verifies any SKILL.md an agent creates or edits with skillci check/eval before treating the change as done.
hn-brief
Personalized Hacker News brief. Ranks today's stories against a stored interest profile, surfaces a few new topics each run, and learns from which links you click.
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.
claude-status-bar
Menu bar status indicator for Claude Code: animated spark, elapsed timer, and open/close lifecycle.
sipcode
Token-economy observatory for Claude Code: forensic per-session audit, A/B savings verifier, reproducible benchmark, and cost prediction — directly in Claude chat. Auto-installs via npx on first use; no separate npm install required.
claude-security-skills
Security skills for Claude Code: secret scanning, Python SAST, prompt-injection testing, and HTTP, JWT, Dockerfile, CORS and dependency auditing. Runs on the standard library with no runtime dependencies.