Skill Claude Code
AWS infrastructure policy for fermi-agentcore - all changes through CDK committed to main, Fermi AWS access is read-only verification.
not rated 1 4d ago A 32 tokens
original MIT
Skill Claude Code
Authenticate single-page apps in Fermi browser sessions by injecting tokens into localStorage AND document.cookie, with secret resolution in evaluate/setCookies.
not rated 1 4d ago A 31 tokens
original MIT
github-api
03Skill Claude Code
Call the GitHub REST API from Fermi (issues, PRs, file commits, binary commits via Git Data API) with correct auth and UTF-8 handling.
not rated 1 4d ago A 36 tokens
original MIT
Skill Claude Code
Shopify Admin API access for Primal TCG - clientcredentials token mint (24h expiry) and X-Shopify-Access-Token request pattern.
not rated 1 4d ago A 34 tokens
original MIT
totp-oauth
05Skill Claude Code
Fermi's own OAuth 2.0 + TOTP owner authentication - how clients connect, how the 2FA login works, and how to roll it back.
not rated 1 4d ago A 38 tokens
original MIT
Skill Claude Code
Hand a task from a Claude Code agent to Grok Bot (the owner's Chief of Staff) via the Fermi grok-bot queue and wait for the result.
not rated 1 4d ago A 40 tokens
original MIT
Skill Claude Code
Grok Bot's side of the grok-bot queue — claim handed-off tasks, fan them out to sub-agents, and complete them with one result.
not rated 1 4d ago A 39 tokens
original MIT
muse-handoff
08Skill Claude Code
Hand a task from a Claude Code agent to Muse (Meta's personal agent) via the Fermi muse queue and wait for the result.
not rated 1 4d ago A 32 tokens
original MIT
muse-inbox
09Skill Claude Code
Muse's side of the muse queue — claim handed-off tasks from Fermi, do them, and complete them with one result.
not rated 1 4d ago A 30 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: