dsh-consumer-audit
Audits a DSH profile for capabilities nothing consumes: inventories the declared composition rows, counts how often each registered tool and skill is actually called in the session logs, separates calls that were made from calls that returned a result, and reports the ones with no observed consumer. Ships a skill that fixes the evidence-chain format for completion claims.
审计 DSH profile 里没有消费者的能力:清点已声明的组成行,统计每个已注册工具与 skill 在会话日志里真正被调用的次数,把「发起过调用」与「返回了结果」分开,报告没有观察到消费者的那些;并附一份固定「完成声明」证据链格式的 skill。
How to install
dsh plugin add github:qimen039-code/dsh-consumer-audit About
dsh-consumer-audit English | 中文 你装的插件或 skill 注册了某项能力,但注册成功不代表模型真的调用过它们,也不代表它们设计的内容真的实际生效了,而这件事模型根本不会主动报告。这个插件负责把它报出来。 它解决什么 DSH 的插件可以向宿主注册工具、skill、服务和路由。注册成功不等于模型会调用它们。 一个插件可能在启动时安静地注册了三个工具,其中两个在过去几十次会话里一次都没被调用过。代码在,测试过,加载正常,只是没有任何任务走到那里。还有一类更隐蔽:插件只包裹了宿主已有的方法,什么都不注册,从清单上看它像什么都没做,实际上它确实在生效。 consumer_audit 把这件事变成一份可核对的清单。它读取活动 profile 的组成行,解析每一行装的是哪个包,静态扫描该包的注册站点,再去 DSH_HOME 下的会话日志里数每个已注册工具和 skill 出现过几次,最后报告计数为 0 的那些。 一份报告长什么样 在装了 8 个插件的 profile 上跑一次,得到这样的结构(插件名换成中性写法): generated_from rows 8 已声明的组成行 sessions_scanned 16 实际扫描的会话日志份数 findings tool_never_invoked some-plugin/tool-x 16 份日志里 0 次调用 tool…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-14
- Created
- 2026-09-12
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
Related plugins
langfuse
langfuse/langfuse
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
claude-code-templates
davila7/claude-code-templates
CLI tool for configuring and monitoring Claude Code
cc-safety-net
kenryu42/claude-code-safety-net
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
loki-mode
asklokesh/claudeskill-loki-mode
Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 8 quality gates.