Enforce human approvals based on risk policy and detected triggers.
Inputs
Mode
Solver + Skeptic + Verifier outputs
risk_policy.yaml
Output
Decision Card(s) if required
Otherwise: "No approval required" + rationale
Rules
If a required approval is missing, stop execution.
Decision Cards must be recorded in the correct decisions_log.md (via user action or MemoryAgent after PASS).
1---2name: approval-gate3description: Skill: ApprovalGateAgent4---5# Skill: ApprovalGateAgent67## Purpose8Enforce human approvals based on risk policy and detected triggers.910## Inputs11- Mode12- Solver + Skeptic + Verifier outputs13- risk_policy.yaml1415## Output16- Decision Card(s) if required17- Otherwise: "No approval required" + rationale1819## Rules20- If a required approval is missing, stop execution.21- Decision Cards must be recorded in the correct decisions_log.md (via user action or MemoryAgent after PASS).
Run npx skillmds@latest add farmountain/approval-gate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Skill: ApprovalGateAgent It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
farmountain (@farmountain) published this skill. Their other Agent Skills are listed on their SkillMD profile.
farmountain