@liyixuan201211

A refutation ledger for coding agents: remember what did not work, and expire it automatically when the code it depended on changes. DSH plugin + CLI, no build step.

DSH plugin: lock, verify and govern AI agent skills. Tells you what a skill can do before you install it — and when it silently gains a capability after your review. Ships no boot-time code.

What can this MCP server actually do — and has it changed since you trusted it? Inspect its declared capabilities, seal them in a lock file, and get told when a later version can do more. Never invokes a tool; gives the server a minimal environment.

Undo what an agent did to a directory: content-addressed snapshots, one-command rewind, and an undo you can undo. Works in any folder — git or not. DSH plugin + skill, zero dependencies.

What will your agent's context cost before it runs? Audit instruction files, skills, MCP tool schemas and memory per source — with duplication, always-on versus on-demand costs, and a budget you can enforce in CI. Reads files and nothing else.

Run an agent unattended for hours and get a morning brief that is an audit, not a summary. Signs a manifest before the work, prices every step at the execution boundary, rolls back a failed verification, and reports what the gate refused. DSH plugin + skill, zero dependencies.

让 AI Agent 听懂音频：转写、鸟种识别、语音情感、环境声与音乐分析。全部本地运行，不用大模型。DeepSeek Harness 技能。