yj-liuzepeng/dsh-project-brain
C3Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval
★ 100+ · yj-liuzepeng/dsh-project-brain source on GitHub · this plugin in the registry
yj-liuzepeng/dsh-project-brain is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands, starts a network server in development tooling the package does not ship, 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 | ×10 in authored code, e.g. src/host/rebuild-sync.js:15, src/host/rebuild-sync.js:15 |
| starts a network server in development tooling the package does not ship | net_server_tooling | ×1 in development tooling the package does not ship, e.g. scripts/smoke-test.mjs:56 |
| reads credential-class env vars | token_env | DSH_LLM_API_KEY |
Services it injects
connection fs llm locale sandboxPolicy sessions slots tools
Hooks it attaches
agent/inbox/claimed agent/session-start project_brain/preview.changed session/disposed
Outbound domains
api.openai.com
Environment variables it reads
DSH_LLM_API_URL DSH_LLM_API_KEY DSH_LLM_MODEL USERPROFILE
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.