Install
$ agentstack add skill-sukoji-loadout-browse ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Loadout — browse the catalog
Read-only. Show what's in the catalog for a chosen domain; do not modify any files.
Steps
- Read
${CLAUDE_PLUGIN_ROOT}/catalog/domains.json,mcp.json,skills.json, andhooks.json. - If the user named a domain (or a stack that maps to one), use it. Otherwise list the domain
titles from domains.json and let the user pick one with AskUserQuestion.
- For the chosen domain, resolve its
loadoutids into the actual items and print them grouped by
kind (MCP servers / Hooks & settings / Skills), each as name — description, with the homepage link and any auth/note caveat.
- End by pointing the user to
/loadout:recommendif they want these profiled against their actual
repo and applied automatically. Mention that token-saver skills (e.g. caveman) are not in browse — /loadout:recommend asks about those separately after the stack loadout.
Keep it scannable. This is the "read the shelf" mode; recommend is the "gear me up" mode.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sukoji
- Source: sukoji/loadout
- License: MIT
- Homepage: https://www.npmjs.com/package/claude-loadout
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.