Zoria-Lind/dsh-token-optimizer
C3Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
★ 10+ · Zoria-Lind/dsh-token-optimizer source on GitHub · this plugin in the registry
Zoria-Lind/dsh-token-optimizer is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands, reads credential-class env vars.
Installable plugin — declares a dsh.bundle manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| executes system commands | exec | ×2 in authored code, e.g. src/modules/text2img.js:16, src/modules/text2img.js:112 |
| reads credential-class env vars | token_env | DEEPSEEK_API_KEY, DSH_TOKEN_OPTIMIZER_DEBUG |
Hooks it attaches
agent/created agent/disposed agent/pre-step agent/status session/disposed session/event tools/change tools/execute tools/post-execute
Outbound domains
api.deepseek.com
Environment variables it reads
DSH_TOKEN_OPTIMIZER_DEBUG DEEPSEEK_API_KEY DSH_ROOT APPDATA DSH_HOME
How to read this
Levels measure capability surface and transparency, not maliciousness. A C3 plugin can be entirely legitimate — a desktop shell genuinely needs subprocesses. The point is that you can see this before installing. See the levels explained and how dsh plugins work.
Findings come from static analysis of shipped code; nothing is executed. Think a flag is wrong? Open an issue — every flag cites the file and line it came from.