DeepSeek Harness plugin

dsh-agent-doctor

DeepSeek Harness health and safety diagnostics for effective tool surfaces, approvals, and AgentFuse composition

Jump to install

Source facts

Repository
MkaliezZ/dsh-agent-doctor
Latest update
Aug 19, 2026
Category
Workflow & Automation
GitHub stars
0
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/MkaliezZ/dsh-agent-doctor
Plugin: dsh-agent-doctor
Author: MkaliezZ

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer3 files
README.mdSource · read only

dsh-agent-doctor

A small DeepSeek Harness (DSH) health and safety diagnostics plugin.

/doctor inspects the effective model-visible tool surface for the receiving agent and reports bounded configuration signals without claiming to be a security scanner, sandbox, or danger classifier.

v0.1 checks

  • model-visible tool count and names;
  • whether reserved run_code is visible;
  • heuristic warning for obviously side-effect-shaped tool names;
  • optional AgentFuse presence requirement;
  • optional approval-service availability signal.

The name-based side-effect check is a diagnostic hint only. It does not authorize or block execution. Use a real runtime policy boundary such as AgentFuse for enforcement.

DSH integration

This repository is intended to be mounted as a DSH bundle. DSH is currently Developer Preview; the plugin targets the pinned public architecture where human commands are registered through ctx.commands and effective tool schemas are exposed by ctx.tools.

- id: dsh-agent-doctor
  name: '@mkaliezz/dsh-agent-doctor'
  config:
    requireAgentFuse: false
    forbidRunCode: true

Run /doctor from an interactive DSH surface after the bundle is composed.

Development

npm test

The core checker has no runtime dependencies and is tested independently of the DSH monorepo. A monorepo compatibility proof should be run against each pinned DSH revision before claiming compatibility.

Non-claims

  • not an antivirus or malware scanner;
  • not a process sandbox;
  • not a policy enforcement boundary;
  • does not prove that a tool is safe from its name;
  • does not prove effective profile immutability.

License

MIT