Token efficiency: tools for developers
Tools that reduce token costs, compress context or cache LLM requests. An entry can appear under several use cases when its topics or description provide several explicit signals.
Use case
Activity
Sort by
87 entries in this view.
Tool ranking
Ranked by measured growth, normalized across sources. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.
- 1Dormant
Spiderbrain-V3
SkillSpiderBrain v3 is a multi-platform skill/framework to reduce token usage and AI hallucinations across Claude, Cursor, and other AI tools.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/abhishek-performdigital/Spiderbrain-V3 ~/.claude/skills/Spiderbrain-V365GitHub starsstable - 2Active
Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable
mcpmeasured growthOpen source ↗
Install
claude mcp add token_optimizer -- uvx slimctx1GitHub starsstable - 3Active
mcp-recall
Skillmcp-recall compresses MCP tool outputs (94 KB → 3.5 KB · 96%) and stores full results in SQLite for retrieval — up to 30x more tool calls per session for heavy MCP workloads.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add sakebomb/mcp-recall8GitHub starsstable - 4Dormant
claude-teams-brain
SkillGive your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add Gr122lyBr/claude-teams-brain26GitHub starsstable - 5Active
governor
SkillClaude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add 0xhimanshu/governor133GitHub starsstable - 6Active
webfetch
SkillOwn your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with…
githubmeasured growthOpen source ↗
Install
git clone https://github.com/firish/webfetch ~/.claude/skills/webfetch55GitHub starsstable - 7Active
quiv
SkillThe Agent Knowledge Kit & Architecture System — 10–32x token-efficient architecture discovery for AI coding agents
githubmeasured growthOpen source ↗
Install
git clone https://github.com/chama-x/quiv ~/.claude/skills/quiv3GitHub starsstable - 8Dormant
bonsai
SkillDrop-in Cursor rules to cut AI response tokens (no filler/hedging, preserve code + technical strings). Includes local, reproducible benchmarks.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/marcomondelli/bonsai ~/.claude/skills/bonsai0GitHub starsstable - 9Active
lazy-cat
SkillClaude Code skills for developers who code like cats — never more effort than the problem requires.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/albertobarnabo/lazy-cat ~/.claude/skills/lazy-cat50GitHub starsstable - 10Active
skill-manager
SkillAutomatically detect and disable irrelevant Claude Code skills per project to save tokens and streamline your tech workflow.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/mrdenox109-nyx/skill-manager ~/.claude/skills/skill-manager5GitHub starsstable - 11Active
super-token-saver
SkillRestore prior Claude Code AND Codex sessions with zero LLM calls. Cross-tool session handoff, cache-expiry prevention, real cost dashboard. One plugin, both hosts.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add ww-w-ai/super-token-saver31GitHub starsstable - 12Active
Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add NodeNestor/claude-rolling-context31GitHub starsstable - 13Active
claude-code-eco
SkillEco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our…
githubmeasured growthOpen source ↗
Install
/plugin marketplace add sup3x/claude-code-eco33GitHub starsstable - 14Active
pdf-text-router
SkillA Claude Code hook that routes each Read on a PDF to the path that actually works: text layer to UTF-8 text, scans to vision, and neither one through poppler.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add WatsonTsai/pdf-text-router7GitHub starsstable - 15Active
Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.
mcpmeasured growthOpen source ↗
Install
claude mcp add gate402-mcp -- npx gate402-mcp2GitHub starsstable - 16Dormant
unclog
MCPAudit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.
githubmeasured growthOpen source ↗
35GitHub starsstable - 17Active
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
mcpmeasured growthOpen source ↗
Install
claude mcp add tokentrust -- uvx tokentrust-cli0GitHub starsstable - 18Active
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
mcpmeasured growthOpen source ↗
Remote server, to be declared in the MCP configuration
https://mcplint-web.vercel.app/api/mcp0GitHub starsstable - 19Dormant
token-reducer
Skill⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add Madhan230205/token-reducer44GitHub starsstable - 20Active
Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads
mcpmeasured growthOpen source ↗
Install
claude mcp add densely -- uvx densely6GitHub starsstable - 21Dormant
Convert long AI conversations into portable conversation state graphs for LLM handoffs.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/Adityapal67/context-graph-compressor ~/.claude/skills/context-graph-compressor35GitHub starsstable - 22Active
ratel
MCPContext engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
githubmeasured growthOpen source ↗
433GitHub starsstable - 23Active
cc-hud
SkillCompact Claude Code statusline — zero-dependency, crash-free on Windows
githubmeasured growthOpen source ↗
Install
/plugin marketplace add WaterTian/cc-hud8GitHub starsstable - 24Active
Usage-aware status line for Claude Code: session & weekly rate-limit gauges with reset countdowns and a precise context-window meter, plus tokens, git & weather. Template-driven and extensible — set it up by chatting with Claude or via a…
githubmeasured growthOpen source ↗
1GitHub starsstable - 25Active
Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen
mcpmeasured growthOpen source ↗
Install
claude mcp add vision-squeezer -- npx vision-squeezer2GitHub starsstable