Skip to content
dsh.fish

Browse

12 results

Bundle

@deeptrial/dsh-bash-rtk

DeepSeek Harness bash executor plugin that routes eligible commands through rtk (Rust Token Killer) to compress tool output and save tokens. Optional overlay: install, then enable via --patch.

DeepTrial14
Bundle

dsh-mcp-lazy

Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.

wings18486
Bundle

dsh-model-info-hint

Show a hover hint with a model's full configuration (input types, context window, max tokens, protocol, base URL, credential env, …) over each model in the DeepSeek Harness web model picker, read from ~/.dsh/settings.yaml.

jackie24551
Bundle

dsh-skill-lazy

DSH skill 目录懒加载:首轮只注入名字+一行短摘要(~500 tokens),完整摘要走 skill_search 按需检索,调用频率排序。

boomzikazita
Bundle

@dsh-external/dsh-peak

DeepSeek API Peak & Off-Peak (50% Discount) status indicator plugin for DeepSeek Harness (DSH)

ibrhr
Bundle

dsh-jwt

DSH plugin: decode and inspect JWT tokens (debug only, no signature verification).

ZhijiangTang
Bundle

dsh-adaptive-max-tokens

Adaptive output-token budgeting for DeepSeek Harness: shrink maxTokens as context fills, restore it after compaction, and retry recognized output-budget overflows once.

3289192-bot
Bundle

@local/tokensqueezer

TokenSqueezer: cuts token use on the model's own output — caps generation before the call, folds verbose answers and reasoning after it, and keeps fenced code byte-identical.

boxiaolanya2008
Bundle

@zzxxxxxx/dsh-dcp

Dynamic context pruning for DeepSeek Harness — model-driven compaction and duplicate-output pruning. | DeepSeek Harness 的动态上下文裁剪:模型驱动的压缩与重复工具输出去重

zzzxxxxxxxxxx
Bundle

dsh-jev-judge

A judgment kernel for coding agents: bounded questions a small Jev judge answers, so the main model keeps its context and tokens for real reasoning.

HunterXing