Per-channel strict prompts, mention gating, silent observation, and a communication autonomy policy for agents that sit in shared channels with external counterparties. Use when an agent joins group chats, shared channels, or DMs where outsiders can read every message and you need it to speak only when addressed, never leak internal context, and route risky content to draft-only approval.
Install
npx skills add affaan-m/ECC --skill counterparty-channel-discipline-eccnpx skills add affaan-m/ECC --skill counterparty-channel-discipline-ecc -a claude-code -gnpx skills add affaan-m/ECC --skill counterparty-channel-discipline-ecc -a codex -ggemini skills install https://github.com/affaan-m/ECC.git --path skills/counterparty-channel-disciplinegh skill install affaan-m/ECC counterparty-channel-discipline-eccgit clone --depth 1 https://github.com/affaan-m/ECC /tmp/affaan-m__ECC
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/affaan-m__ECC/skills/counterparty-channel-discipline ~/.claude/skills/counterparty-channel-discipline-ecc # Claude Code
cp -R /tmp/affaan-m__ECC/skills/counterparty-channel-discipline ~/.agents/skills/counterparty-channel-discipline-ecc # Codex, Cursor, Gemini CLI, Copilot, OpenCode