GanyuanRan/Aegis

C3

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

★ 1.0k · GanyuanRan/Aegis source on GitHub · this plugin in the registry

GanyuanRan/Aegis is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands.

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./extensions/dsh/cordis.patch.yml
executes system commandsexec×5 src, e.g. .opencode/plugins/aegis.js:12, skills/writing-skills/render-graphs.js:18

Services it injects

agents skills

Hooks it attaches

agent/session-start

Environment variables it reads

AEGIS_ACTIVATION_MODE AEGIS_TDD_MODE USERPROFILE AEGIS_METHOD_PACK_ROOT OPENCODE_CONFIG_DIR

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.