Statically enforce a privacy/redaction boundary on an artifact tree before publication, the way an AST checker enforces a code contract. Builds a two-tier gate — a shape-based deny-list (regex over identifier shapes) plus a structure-aware tier that parses JSON/HTML/SVG/Markdown/code and asserts sensitive content cannot appear in meaningful positions — with a strict exit-code contract…
Install
npx skills add pjt222/agent-almanac --skill enforce-redaction-gatenpx skills add pjt222/agent-almanac --skill enforce-redaction-gate -a claude-code -gnpx skills add pjt222/agent-almanac --skill enforce-redaction-gate -a codex -ggemini skills install https://github.com/pjt222/agent-almanac.git --path skills/enforce-redaction-gategh skill install pjt222/agent-almanac enforce-redaction-gategit clone --depth 1 https://github.com/pjt222/agent-almanac /tmp/pjt222__agent-almanac
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/pjt222__agent-almanac/skills/enforce-redaction-gate ~/.claude/skills/enforce-redaction-gate # Claude Code
cp -R /tmp/pjt222__agent-almanac/skills/enforce-redaction-gate ~/.agents/skills/enforce-redaction-gate # Codex, Cursor, Gemini CLI, Copilot, OpenCode