Token efficiency

Measured catalogue entries associated with Token efficiency.

121 measured catalogue entriesSnapshot measured Oct 22, 2026Sort: Momentum

Refine this view

Language
Any language

Measured resources

Page 7 of 13

  1. claude-teams-brain

    SkillDormant

    Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.

    Source
    GitHub
    Language
    Python
    Last activity
    Mar 15, 2026

    Stars29Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  2. senior-fable

    SkillActive

    Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.

    Source
    GitHub
    Last activity
    Oct 1, 2026

    Stars28Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  3. permafrost

    SkillDormant

    Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.

    Source
    GitHub
    Language
    Python
    Last activity
    Jun 23, 2026

    Stars24Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  4. laconic

    SkillDormant

    Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

    Source
    GitHub
    Language
    Python
    Last activity
    Jul 12, 2026

    Stars24Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  5. aigent-os

    SkillActive

    Claude Code harness that refreshes its own context instead of compacting: at a threshold it writes a verified capsule, runs /clear, and resumes in a fresh session. Memory is plain markdown in git, readable with git log. MIT, runs locally, one install (Node 18+). Codex adapter included.

    Source
    GitHub
    Language
    JavaScript
    Last activity
    Oct 22, 2026

    Stars23Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  6. io.github.Arrayo/smart-context-mcp

    MCP serverUnknown

    Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.

    Source
    MCP registry
    Last activity
    No activity date supplied

    Downloads · last 7 days107Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  7. llmtrim

    MCP serverUnknown

    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

    Source
    MCP registry
    Last activity
    No activity date supplied

    Downloads · last 7 days101Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  8. catalyst

    SkillActive

    Deprecated — Catalyst local runtime, kept for history. Use coalesce-labs/catalyst-dev-skills and coalesce-labs/catalyst-cloud-skills.

    Source
    GitHub
    Language
    JavaScript
    Last activity
    Sep 29, 2026

    Stars20Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  9. pdf-decompiler-mcp

    MCP serverActive

    A MCP that turns PDFs into structured text, tables, figures, metadata, annotations, and page-level evidence for selective retrieval by MCP-compatible AI agents. Improves the information quality AI agents receive while also reducing token costs in some scenarios.

    Source
    GitHub
    Language
    JavaScript
    Last activity
    Aug 4, 2026

    Stars17Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change

  10. voly

    AgentActive

    Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

    Source
    GitHub
    Language
    Python
    Last activity
    Oct 5, 2026

    Stars17Measured · Oct 22, 2026

    Momentum07 days · Measured · 0% relative change