evo-subagent

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.

PluginAI ModelsKnowledgeMemory

Verification

L2 · Structured

Security

Low

Health

Active

Trust

Silver

What it does

Installation

dsh plugin --profile web add github:ZekaiShi/evo-subagent

Install method: GitHub · no verification record (L1-L5)

Compatibility

DSH Version	Status
not stated	no verification record

Requirements

• Node.js: not stated
• DSH: not stated
• External credentials: none detected

Security Report

Automated static scan, not manual review.

DSH.SO VETPASSEDfbf75e

Security reviewAutomated review · daily

PASSED

Vet static analysis found no suspicious behavior — verdict is clean.

0 critical·0 high·1 medium·94 score

Version binding

plugin version0.5.0dsh manifest

scanned commitfbf75e1b9b702026-08-24

latest commit9c7d737de596

vet verdictclean · gitscore 94

Vet is an AST static scan (npm artifact or git source).

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Risk details

No critical or warning findings.

Activity

Last commit 2026-08-24 · activity: Active

• Repo created: 2026-08-24

• Stars: ★ 2 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/ZekaiShi/evo-subagent

Plugin notes

What is the evo-subagent DeepSeek Harness plugin?

evo-subagent is a DeepSeek Harness plugin maintained by @ZekaiShi. It is cataloged on dsh.so as a AI Models plugin for Memory tasks, with a public GitHub source, declared install command, and automated static security scan.

How do I install evo-subagent?

Run dsh plugin --profile web add github:ZekaiShi/evo-subagent in a DeepSeek Harness (dsh) environment. The command is parsed from the plugin manifest, but it has not yet been tested in an isolated container at the L3+ level.

Is the security scan on this page a manual audit?

No. The scan is an automated heuristic review of the repository source and can produce false positives. It is not a manual security audit and never an endorsement; review the repository and installed permissions before using the plugin.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-08-24