PerryLink/dsh-memento
C2Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness: a ctx.memory capability seam with a zero-dependency SQLite provider, a memory tool, and frozen snapshot injection
★ 100+ · PerryLink/dsh-memento source on GitHub · this plugin in the registry
PerryLink/dsh-memento is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes commands in development tooling the package does not ship.
Installable plugin — declares a dsh.bundle manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| can rewrite the system prompt | prompt_surface | approval, systemPrompt |
| executes commands in development tooling the package does not ship | exec_tooling | ×10 in development tooling the package does not ship, e.g. scripts/check-coverage.mjs:64, scripts/check-lockfile-drift.mjs:15 |
Tool registrations
4 confirmed registration point(s); analysis is incomplete.
index.mjs:453tool factoryindex.mjs:1160tools.registerindex.mjs:1214tools.registerindex.mjs:1906tool factoryindex.mjs:1086Context or tools service passed to an unresolved helper
Services it injects
approval slots systemPrompt tools
Hooks it attaches
approval/request internal/service loader/volatile-update session/event
Environment variables it reads
DSH_MEMENTO_DB_PATH 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.