一键导入
governance-approval
The R-008 human-gate workflow for rules, permissions, model-routing, and security posture changes — never an automated rewrite.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
The R-008 human-gate workflow for rules, permissions, model-routing, and security posture changes — never an automated rewrite.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | governance-approval |
| description | The R-008 human-gate workflow for rules, permissions, model-routing, and security posture changes — never an automated rewrite. |
Enforce R-008 (human gate) for all changes to rules, permissions, model routing,
and security posture. This skill describes the workflow the system-lead follows
when a change requires human approval — it does not implement the mechanism (that
is the governance CLI verb and subagent, built separately).
rules/** or .aspis/rules/**.**/permissions*.yaml or .claude/settings.json..opencode/agents/** or .claude/agents/**.rules/**, .aspis/rules/****/permissions*.yaml, .claude/settings.json.opencode/agents/**, .claude/agents/**aspis governance request --paths <paths> --reason "<why this change is needed>"
to record the intent in the approval ledger.aspis governance approve <request-id> --approver <name>.--force. Do not use an env-var override. There is no bypass..aspis/state/approval-ledger.yaml (via the
aspis governance request command).approve command.--glob-approval) for convenience — pattern-level
approval is a dangerous extension that requires explicit confirmation.Keep commits atomic — split a mixed change set into scoped, reviewable commits.
The one-time procedure to take an exported project to live — understand it, confirm the name/goal/stack with the user, run the deterministic `aspis bootstrap`, enrich the judgment files (AGENTS.md, ARCHITECTURE, context), verify, and let the package self-clean. Followed by the bootstrap agent.
Keep per-subsystem architectural intent current through the planning loop — read before designing, record an impact report on change, confirm with the user, apply a dated update, and verify the build against approved intent.
Audit a plan's task dependency graph for structural integrity — circular dependencies, missing prerequisites, orphan tasks, and dependency classification (hard/soft/warning). Produces a pass/warn/fail audit report per dependency so planners catch graph errors before build starts.
Every editing agent should start on a clean working tree so parallel work never collides.
Verify hooks ran, no secrets, protected paths untouched, and commit message valid before committing. Owned by the reviewer.