vibe-skill
pcx-wave
Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage
GITHUB TOPIC
14projects include this topic
The "token-optimization" topic on GitHub groups 14 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by vibe-skill with 118 GitHub stars. vibe-skill — Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
pcx-wave
Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage
jimoto-no-llm
Rust launcher for DSH with native fast commands, guarded agent tools and a local project dashboard
One model writes the work, a different one reviews it, and neither decides whether it passed. Cross-provider AI review with verifiable evidence, for DeepSeek Harness/Cordis hosts. 中文文档见 README.zh.md。
123caiji
Memory and token-optimization plugin toolkit for DeepSeek Harness: cross-session knowledge graph memory + five-layer token-saving orchestration.
chiro2001
DeepSeek Harness dynamic context management plugin (Dynamic Context Pruning for dsh), benchmarked against opencode-dcp
kpl0111
Token-efficient tool-result pruning for DeepSeek Harness: compact previews, targeted recall, and long-session context control.
Nigel211
Render long text as images to send, capping at 384 tokens per image to compress LLM input tokens — a plugin built for DeepSeek Harness; Pack long text into images to cut LLM input tokens (384/image cap) — a DeepSeek Harness plugin.
Snow-ea
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness.
yzsp-studio
🔥 Cut 91% of tokens, lose zero capability | 省 91% token · 能力零损失 — Scope DSH skill catalogs & MCP tool schemas per workspace. Measured: 36,870 → 11,658 tokens/step (−68%). Nothing deleted. | 按工作区裁剪技能目录与工具 schema,每步降 68%,一个字都不删。📮 wow.vip@foxmail.com
dcd887
Token-saving interceptor for DSH tool calls: dedupe cache, executable decision graph, live session state, honest ledger.
maxeone
Context Language Models (CLM) for DeepSeek Harness: Active editable context window mirrored to disk for pruning and token optimization.
wings1848
RTK command rewriting and tool-output compaction for the DeepSeek Harness: rewrites bash commands to their rtk equivalents and compacts the result before the model sees it.
wsxuyue
DSH plugin: shrink the tool-definition block sent on every request (~39% fewer tokens) without changing tool behaviour
xarleyn
MOVED to @yadsh/dsh-sleev in xarleyn/dsh-plugins — Sleev integration for DeepSeek Harness with route-aware LLM telemetry and context-optimization observability