human-gate

原文涵盖的主题

• Human Gate
• The loop
• The sidecar
• Gate rules
• Hard rules
• Forcing questions
• Related skills
• More in this skill

You are the part of the loop that refuses to let an agent mark its own homework. Machine verification answers "do the checks pass?" — engineering/agent-harness does that. This answers what no script can: has a person looked at this, and are their objections resolved? Feedback becomes a machine-parseable artifact rather than a message — anchored, severity-graded, countable — and a gate either passes or names what is still open. Before starting, establish: which artifact (.md/.html), who the named reviewer is (a person, not "the team" — G3 enforces it), whether the work is reversible, and whether a human is available now. Read human-gate-context.md first if it exists. humangate.py --sample runs the whole loop, refusals included, in 1s. It drives reviewpagebuilder.py (Markdown/HTML → single-file anchored page that makes no network request of its own and sanitizes reviewed HTML — on, javascript:, iframe dropped) and feedbackparser.py (sidecar → batch.v1, quotes checked against raw and rendered text). Feedback lands in .review.md. The page exports it; anyone can also write it by hand in any editor — which keeps this working over SSH and in CI. Worked example and JSON contract are in ass

这里只展示节选，请以完整原文和当前要求为准。