Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/alibaba/anolisa/skillfs-mountnpx skills add alibaba/anolisa --skill skillfs-mountgit clone --depth 1 https://github.com/alibaba/anolisaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alibaba/anolisa/skillfs-mount)<a href="https://agentmods.dev/skills/alibaba/anolisa/skillfs-mount"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/skillfs-mount.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00106 | $0.01548 |
| Opus 5 | $0.00053 | $0.00774 |
| Sonnet 5 | $0.00021 | $0.00310 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
skillfs-mount scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skillfs 配置与挂载指南
前提条件
skillfs已安装(RPM 包),运行skillfs --version确认- 系统已安装
fuse3(若缺失:yum install -y fuse3) - 确认 skills 源目录路径(openclaw 用户通常为
~/.openclaw/skills)
操作流程
STEP 1:了解用户类型,确定主视图
有使用历史的用户(openclaw):
运行脚本分析历史调用频次,按调用次数决定哪些 skill 进主视图:
# 分析 openclaw session 日志中的 skill 使用频次(默认读 ~/.openclaw)
python3 <skill_dir>/scripts/skill_usage_from_session_logs.py
# 分析 copilot-shell (cosh) chat 日志中的 skill 调用统计(默认读 ~/.copilot-shell)
python3 <skill_dir>/scripts/skill_usage_from_chat_logs.py
两个脚本都支持 --logs-dir 指向自定义日志目录。
输出示例:
=== Skill Invocation Statistics ===
github: 42
slack: 28
tmux: 17
weather: 3
调用频次高的 skill 建议放入主视图,频次低或从未使用的放入次级视图。
纯新用户(无历史):
列出 skills 目录内容,按用途给出分类建议:
ls ~/.openclaw/skills/
常见分类建议:
- 主视图(高频核心):代码工具、版本管理、常用 API 集成
- 次级视图:不常用工具、实验性 skill、特定场景用途
STEP 2:生成 skillfs-views.toml
根据分析结果,运行 classify 命令生成初始配置:
skillfs classify ~/.openclaw/skills --primary-count 8
生成的 ~/.openclaw/skills/skillfs-views.toml 结构(视图名称固定为 major / other):
[[view]]
name = "major"
default = true
description = "Core skills shown at mount time"
skills = ["github", "slack", "tmux", ...]
[[view]]
name = "other"
default = false
description = "Additional skills accessible via skill-discover"
skills = ["weather", "notion", ...]
挂载行为由
default = true/false决定,视图名称仅作为 skill-discover 中的分组标题显示。
按分析结果手动调整:直接编辑 views.toml,在两个 skills 列表之间移动 skill 名称。
⚠️ views.toml 中的字符串必须与 skill 的目录名完全一致,否则该技能将从视图中 消失。目录名是权威的 skill key;
SKILL.mdfrontmatter 里的name:只是展示元数据, 不参与视图匹配,重命名目录后也不会覆盖目录 key。
STEP 3:挂载
# 原地挂载(推荐):Agent 访问同一路径,FUSE 透明过滤内容
skillfs mount ~/.openclaw/skills ~/.openclaw/skills \
--pid-file /tmp/skillfs.pid \
--log-file /tmp/skillfs-{pid}.log &
sleep 1
# 确认挂载成功
ls ~/.openclaw/skills/ # 应只显示主视图 skill + skill-discover
挂载时自动将未出现在 views.toml 中的新 skill 追加到默认视图。
需要长期保持挂载时改用 managed 模式:它启动一个 detached supervisor,worker 意外退出后 会自动重挂,不需要自己管理 pid file。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 178 lines · 106 tokens per session scan A 9fb51a57bb94
skillfs-mount is a skill published in the GitHub repository alibaba/anolisa (618 stars, last pushed today), licensed Apache-2.0. It adds 106 tokens to every session and 1,548 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
beevibe-verify-pr
CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…
beevibe-pre-task-setup
Cold-start git workspace setup for a fresh beevibe task. Use at the start of a session whose intent has a block but NO or block — i.e. the first dispatch of this task. Checks for an existing repo clone, pulls the base branch if present (clone if missing), prunes any per-task worktrees from earlier tasks whose work has…
beevibe-use-repo
You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.
spec-converge
Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available…
beevibe-discover-repo
Find the best GitHub repo for a goal, then call userepo to run it in a sandbox. Use whenever the user's goal requires a capability you don't have natively and you haven't been given a specific repo.