Jev in production › Agent context and memory

dsh-tokenslash

Jev triages and prunes unused tool schemas in DeepSeek Harness, reducing prompt overhead by up to 85% (vendor).

Open on GitHub ↗

up to 85%measured, as published by the source
Use
Agent context and memory
Industry
Developer tools
Form
Open-source tool
Stage
In production
Plugs into
DeepSeek Harness
Listed
2026-10-08
Found via
github
Repository
JessenReinhart/dsh-tokenslash
Stars
5
Forks
1
Last push
2026-10-09
Language
JavaScript
License
none stated

The README opens with

Cut up to 85% of prompt overhead in DeepSeek Harness. Automatically prune unused tools, strip bloated system prompts, and route subagents to budget-friendly models — without breaking agent workflows.

Every time you hit Enter in DeepSeek Harness (DSH), the system prompt includes every single registered tool schema and plugin guideline — even ones you never touch (image generators, web crawlers, workflow planners).

In a typical desktop setup, that's 50+ tools and ~18,000 tokens of static overhead on every single turn. Over a 10-turn coding session, you burn 180,000+ tokens just telling the LLM what tools exist.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent context and memory