Agent Skills › boshu2/agentops › sbh

sbh

GitHub

SBH技能用于诊断磁盘压力并执行经授权的恢复操作。它遵循证据优先原则，按不可逆性排序执行状态检查、干跑、球释释放及文件清理，严禁未经明确授权进行突变操作，确保存储安全与有效回收。

skills/sbh/SKILL.md boshu2/agentops

触发场景

用户请求诊断磁盘空间不足或高负载问题用户请求对特定挂载点进行存储恢复或清理

安装

npx skills add boshu2/agentops --skill sbh -g -y

更多选项

不安装直接使用

npx skills use boshu2/agentops@sbh

指定 Agent (Claude Code)

npx skills add boshu2/agentops --skill sbh -a claude-code -g -y

安装 repo 全部 skill

npx skills add boshu2/agentops --all -g -y

预览 repo 内 skill

npx skills add boshu2/agentops --list

SKILL.md

Frontmatter

{
    "name": "sbh",
    "consumes": [],
    "metadata": {
        "tier": "execution",
        "effects": [
            "delete_reclaimable_files",
            "release_disk_ballast",
            "modify_host_storage_config"
        ],
        "disposition": "keep_optional_adapter",
        "capabilities": [
            "sbh"
        ],
        "dependencies": [],
        "canonical_status": "canonical"
    },
    "produces": [],
    "practices": [
        "pragmatic-programmer"
    ],
    "context_rel": [],
    "description": "Inspect disk pressure with SBH and perform an authorized recovery action. Use when: storage diagnosis or SBH recovery is requested; inspection does not authorize deletion.",
    "hexagonal_role": "supporting",
    "user-invocable": true,
    "output_contract": "disk pressure observations and authorized action result",
    "skill_api_version": 1
}

SBH — storage pressure specialist

SBH exposes disk-pressure status, ballast, scanning, and recovery commands. This skill gathers evidence and performs at most the explicit action authorized by the caller. Its authorized actions can delete files and change host storage configuration, so no mutation runs without explicit caller authority. The command surface below is anchored to sbh 0.4.27; re-verify against sbh --version on another host before relying on an exact flag.

Evidence-first recovery works because disk pressure has cheap reversible remedies and expensive irreversible ones; a factual baseline is what tells them apart before anything is deleted. Order remediation by irreversibility: status and dry runs first, ballast release next, cleanup of unprotected files after that, and emergency deletion last — never skip forward while a more reversible step remains untried.

Named failure mode — wrong-mount relief: reclaiming gigabytes on a filesystem that is not the constrained mount and declaring the pressure resolved.

Anti-pattern: escalating straight to emergency --yes because pressure is critical. Corrective: urgency raises the stakes of an irreversible mistake; it never lowers the authorization bar or the ordering above.

Constraints

Begin with sbh --json status, sbh check, or a dry run on the exact mount because recovery decisions need a factual baseline.
Never run clean --yes, emergency --yes, ballast release, tune --apply, unprotect, or service/configuration changes without explicit authority because those operations mutate host state.
Preserve .git/, open-file, young-file, non-writable-parent, and .sbh-protect vetoes because they prevent unsafe or ineffective cleanup.
Confirm that ballast or reclaimed bytes affect the constrained mount because free space on another filesystem does not resolve the pressure.
Run one action once, capture before/after evidence, and stop because the caller owns any further mutation. A negative result is returned to the caller; this skill does not retry or escalate it.

Output

Return mount, free bytes, pressure state, dry-run candidates, authorization used, exact command and exit code, bytes reclaimed, protection vetoes, and checked/not checked surfaces.

Full command documentation: https://github.com/Dicklesworthstone/storage_ballast_helper

版本历史

9f8a711 当前 2026-09-22 11:04
7b07a7d 2026-08-19 22:06
W7版本更新：修正了手稿模式真实性、DCG事实纠正及诚实支持契约；为sbh技能声明了真实效应，定义了双工具缺失和破坏性表面，缩小了实时输出夸大描述，并固定了版本号。
3f402e5 2026-07-24 22:12