17 tagged token optimization, measured the same way as everything else here.
Instructions file GitHub Copilot
Instructions for yvgude/lean-ctx, a project described as: Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the…
Instructions file CodexOpenCode
Instructions for yvgude/lean-ctx, covering context engineering layer, mandatory multi-agent delivery, integration mode: replace, subagent compatibility (cursor / claude code) and cli commands (optimized shell, lower overhead).
Instructions file CodexOpenCode
Instructions for juyterman1000/entroly, covering agents.md, use gstack with codex, entroly operating rule, default codex workflow and ui verification rule.
Instructions file
Instructions for juyterman1000/entroly, covering claude.md, gstack operating protocol, default workflow, entroly trust invariants and review checklist.
Instructions file
Instructions for edouard-claude/snip, covering claude.md, project overview, key concept, repository structure and architecture.
olivomarco/github-copilot-token-optimization
Instructions file GitHub Copilot
Copilot instructions for olivomarco/github-copilot-token-optimization: Terse like caveman. Technical substance exact. Only fluff die. Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged. Pattern: [thing] [action] [reason]. [next step]. ACTIVE EVERY…
Instructions file GitHub Copilot
Copilot instructions for DFKHelper/token-goat: Gate — before every file read, answer one question first: is there a token-goat command that returns just what I need? If yes, run it. A read tool invoked without answering the gate is a violation, not an oversight. The gate is per file: batched or parallel reads do not…
Instructions file CodexOpenCode
AGENTS.md instructions for DFKHelper/token-goat, covering agents.md, project, build, test, lint, the index must stay bounded and security boundaries.
Instructions file
Instructions for ww-w-ai/super-token-saver, covering claude.md, what this is, architecture, two transcript sources, one pipeline and one repo, two hosts.
Instructions file CodexOpenCode
Instructions for phonowell/invoke-opencode-acp, a project described as: Claude Code CLI skill that delegates complex tasks to an OpenCode subagent via ACP protocol, saving 50-90% tokens.
Instructions file
Instructions for phonowell/invoke-opencode-acp, covering invoke-opencode-acp, 关键约束, skill 使用, 技术栈 and 核心命令.
tinesoft/spec-kit-token-budget
Instructions file
Instructions for tinesoft/spec-kit-token-budget, covering claude.md, what this repo is, development workflow, install locally into an sdd project for manual testing and test slimoutput.sh.
Instructions file
Instructions for dhanushkumarsivaji/kerf-cli, covering kerf-cli — claude code cost intelligence, project overview, architecture, conventions and key paths.
Supersynergy/agent-token-saver-skill-router
Instructions file CodexOpenCode
Instructions for Supersynergy/agent-token-saver-skill-router: Run si outside model context before loading any skill body.
Supersynergy/agent-token-saver-skill-router
Instructions file
Instructions for Supersynergy/agent-token-saver-skill-router: Run si outside model context before loading any skill body.
Instructions file
Claude Code instructions for nickdesi/ZipAI, covering claude.md — zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.
msgtorahul-art/context-skeleton
Instructions file
Claude Code instructions for msgtorahul-art/context-skeleton, covering claude.md - contextskeleton project guidelines, core commands and architecture rules.