Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From oh-my-agent
Checks or sets the oma approval posture (suggest, auto, full-auto) for autonomous workflow control, with guardrails and persistent state.
How this command is triggered — by the user, by Claude, or both
Slash command
/oh-my-agent:approvalThe summary Claude sees in its command listing — used to decide when to auto-load this command
运行 oma 批准姿态管理器。
输入：
$ARGUMENTS
协议：
1. 解析请求的批准姿态。
2. 支持的值：
- `suggest`（默认）：建议操作并要求对副作用进行明确批准
- `auto`：自动批准低风险的常规操作，将高风险操作升级以供批准
- `full-auto`：在无需常规确认的情况下继续，但仍会升级破坏性/高风险操作
3. 如果未提供值，从 `.oma/state/approval.json` 显示当前姿态（如果可用）。
4. 按姿态应用护栏：
- 破坏性操作检查
- 秘密/凭据处理检查
- 生产影响确认检查
5. 如果文件系统工具可用，写入/更新 `.oma/state/approval.json`。
6. 澄清边界：这设置了 oma 策略姿态，不会直接重新配置 iFLOW CLI 运行时批准标志。
建议的 `approval.json` 格式：
{
"mode": "suggest|auto|full-auto",
"side_effect_policy": "confirm|risk-based|autonomous-with-guardrails",
"high_risk_requires_confirmation": true,
"updated_at": "<ISO-8601>",
...运行 oma 批准姿态管理器。
输入： $ARGUMENTS
协议：
suggest（默认）：建议操作并要求对副作用进行明确批准auto：自动批准低风险的常规操作，将高风险操作升级以供批准full-auto：在无需常规确认的情况下继续，但仍会升级破坏性/高风险操作.oma/state/approval.json 显示当前姿态（如果可用）。.oma/state/approval.json。建议的 approval.json 格式：
{
"mode": "suggest|auto|full-auto",
"side_effect_policy": "confirm|risk-based|autonomous-with-guardrails",
"high_risk_requires_confirmation": true,
"updated_at": "",
"source": "oma:approval"
}
输出格式：
| 操作类别 | suggest | auto | full-auto |
|---|
npx claudepluginhub sswym/oh-my-agent --plugin oh-my-agent/pseo-approveUse when: kullanıcı "onayla", "approve", "izin ver", "consent", "şu aksiyona izin" der ya da `/pseo-approve <run_id> <action> <target>` çağırırsa. Also use when: bir AMO run'ı geri-alınamaz/dışa-dönük bir aksiyon (git push / silme / POST / GSC sitemap submit / Indexing URL_UPDATED / oversized DFS) için operatör onayı bekliyor; consent defterine `projects/{slug}/_state/consent.jsonl` hash-chained bir satır yazılacak. Do not use when: aksiyonu fiilen çalıştırma (gate 2b kontrol eder), session bağlama (`/pseo-bind`), portföy-geneli aktif proje set etme (`/pseo-active`) ya da durum görme (`/pseo-status`).
/cc-autonomyDeploys autonomy operating profiles composing memory, workflow, orchestration, hooks, and verification into repo files and hooks. Supports deploy, status, switch, verify, plan subcommands with conservative to unattended-review profiles.
/guardrailsViews guardrails status, tier stats, token cap, and audit log. Manages modes (strict/relaxed/audit/reset), policy, and token cap via subcommands.
/session-autonomousSets the session mode to autonomous, enabling unattended execution of approved GO items with hook-enforced keep-alive.
/approveManages Jira approval workflows: request PR/deploy/release/issue, approve/reject with comments, status/list pending/history, configure.
/ng-decide-authorityDetermines whether an agent may act autonomously or must defer to a human gate, based on reversibility, evidence quality, and consequence severity. Outputs a decision placement and escalation trigger.