xinchen03/minta
C3The context quality layer for AI agents — memory that checks itself: lifecycle governance, calibrated confidence, and staged claim gates. Local-first, MCP 13 tools, DeepSeek Harness plugin.
★ 10+ · xinchen03/minta source on GitHub · this plugin in the registry
xinchen03/minta is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, eval in build output only, 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 |
| eval in build output only | eval_bundled | ×1 in build output only, e.g. web/dist/bundle.92be0971.js:2 |
| reads credential-class env vars | token_env | MINTA_API_KEY |
Hooks it attaches
agent/session-start
Environment variables it reads
MINTA_API_URL MINTA_API_KEY
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.