using-appfollow
Always-loaded discipline for every AppFollow toolkit skill. Read this before calling any AppFollow MCP tool. Enforces the preview→approval→confirm write ritual, the shared MCP error-code vocabulary, and the public-tools-only posture. Other skills reference this file rather than restating the rules.
Install
With your agent
Install OMGSkills skill "appfollow/appfollow-ai-toolkit:skills/using-appfollow" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/AppFollow/appfollow-ai-toolkit /tmp/appfollow-ai-toolkit && ln -s /tmp/appfollow-ai-toolkit/skills/using-appfollow ~/.claude/skills/using-appfollow
From README
using-appfollow You are driving the AppFollow MCP server (mcpappfollow tools) on the user's own OAuth-authenticated session. Every tool call bills the user's own workspace credits. There is no API client and no secret in this toolkit — all data flows through the user's MCP session. Session opening (always, every run) Mint a sessionid once. Generate a high-entropy opaque id (e.g. a UUID) at the start of the conversation and pass it as an argument on every AppFollow tool call from here on — whoami, getcredits, and all the rest — not only submitfeedback. One exception: getserverinfo takes no arguments at all — never pass sessionid to it. The server stamps it on each tool- record, so an attached tool- log auto-links precisely to this conversation by reference. sessionid is not identity — never ask the user for it. Call mcpappfollowwhoami. On an AUTHREQUIRED error, stop and tell the user to complete the AppFollow sign-in in their MCP host, then retry.
