Co-Engram/Co-Engram
C3Self-evolving team memory
★ 5+ · Co-Engram/Co-Engram source on GitHub · this plugin in the registry
Co-Engram/Co-Engram is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes system commands, reads credential-class env vars.
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| can rewrite the system prompt | prompt_surface | systemPrompt |
| executes system commands | exec | ×5 src, e.g. packages/dsh-plugin/src/headless-executor.ts:2, packages/dsh-plugin/src/headless-executor.ts:14 |
| reads credential-class env vars | token_env | ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN |
Services it injects
systemPrompt tools
Outbound domains
api.anthropic.com
Environment variables it reads
ANTHROPIC_API_KEY ANTHROPIC_AUTH_TOKEN ANTHROPIC_MODEL ANTHROPIC_DEFAULT_HAIKU_MODEL ANTHROPIC_BASE_URL NO_COLOR CO_ENGRAM_TEST_DATAROOT
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.