Agent Skills format converges, but harness execution and permissions remain fragmented

Agent Skills 统一了文件格式，Harness 仍然各自为政

The Agent Skills open standard has made .agents/skills/ a shared discovery directory across Codex, Cursor, OpenCode, Gemini CLI, and the Antigravity family. Claude Code is the sole outlier—it only scans .claude/skills/ and requires a symlink bridge. Worse, the same SKILL.md can be found by multiple clients, but Claude Code's 14 private frontmatter fields (model, effort, hooks, disallowed-tools, etc.) are ignored everywhere else. Execution diverges further: Gemini CLI asks for user confirmation before loading skill content, OpenCode requires the model to invoke a skill tool, and Antigravity CLI just uses file tools. Tool names, working directories, and permission policies all differ at runtime. Developers building custom harnesses must supply their own directory scanning, dependency prep, sandboxing, and authorization—format compatibility alone won't cut it.

Why it matters: Hits all three HKR axes: the counterintuitive compatibility gap creates suspense, the precise client list and timeline deliver concrete knowledge, and it directly resonates with multi-tool developers. Score capped at 74 rather than higher because this is a toolchain interopera...