Usage statistics for DeepSeek Harness: aggregated token and cost metering per session, per day, per week, per month and over custom date ranges, with per-model breakdown, peak-hour pricing, durable daily history, a Settings usage panel and the /usage comm

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-performance systems.

Runtime-agnostic Rust port of Cordis, the plugin framework at the core of DeepSeek Harness — scoped dependency injection, lifecycle-owned effects, events, structured logging. Zero dependencies.

Endfield-inspired industrial UI shell for DeepSeek Harness (dsh) — non-official fan theme. Install: dsh plugin --profile web add @rison/dsh-endfield-ui

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.