InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. ratel

    Skills

    Context 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.

    Stale GitHub, ratel-ai 558 ★MITUpdated 5 days ago

    git clone https://github.com/ratel-ai/ratel.git
  2. vibe-skill

    Skills

    Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage

    Stale GitHub, pcx-wave 124 ★Updated 5 days ago

    git clone https://github.com/pcx-wave/vibe-skill.git
  3. Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.

    Indexed GitHub, YahyaLendani 14 ★MITUpdated 2 days ago

    git clone https://github.com/YahyaLendani/opus-tuner-claude-skill.git
  4. Chisle

    Skills

    Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

    Indexed GitHub, JayPokale 1,132 ★MITUpdated 2 days ago

    git clone https://github.com/JayPokale/Chisle.git
  5. Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.

    Stale GitHub, sofumel 8 ★MITUpdated 18 days ago

    git clone https://github.com/sofumel/claude-handoff-revive.git
  6. rote

    Skills

    Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop

    Indexed GitHub, trevhud 8 ★Apache-2.0Updated yesterday

    git clone https://github.com/trevhud/rote.git
  7. TypeScript/Bun tools for coding agents. Run checks once, keep complete evidence, and test output filters against task-specific requirements. No runtime packages.

    Indexed GitHub, Supersynergy 8 ★MITUpdated 3 days ago

    git clone https://github.com/Supersynergy/agent-token-saver.git
  8. kyber-weave

    Skills

    Agentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads, skills, governed project knowledge, quality gates, and local token observability. Human judgment. Agent speed.

    Indexed GitHub, dpalfery 23 ★MITUpdated today

    git clone https://github.com/dpalfery/kyber-weave.git
  9. A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.

    Stale GitHub, russelleNVy 953 ★MITUpdated 5 months ago

    git clone https://github.com/russelleNVy/three-man-team.git
  10. aiwg

    Skills

    Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and MCP tools for Claude Code, Codex, Copilot, Cursor and more, plus SDLC workflows, session memory, and Jev decision support that offloads bounded LLM decisions to save tokens.

    Indexed GitHub, jmagly 230 ★MITUpdated today

    git clone https://github.com/jmagly/aiwg.git
  11. cli2skill

    Skills

    🔧 Turn any CLI or MCP server into an Agent Skill — zero process overhead, 98% fewer tokens. Kill MCP zombie processes. Works with Claude Code, Codex, Gemini CLI & 26+ platforms.

    Stale GitHub, 2233admin 9 ★MITUpdated 26 days ago

    git clone https://github.com/2233admin/cli2skill.git
  12. CoalFace

    Skills

    Fan-out discipline for AI coding agents - scout, partition, wave, QC, single-writer apply, receipt. Bounds a swarm to the solo-cost budget; does not make models smarter. Zero-dependency, Phoenix-13. Part of TheColliery.

    Indexed GitHub, TheColliery 7 ★Apache-2.0Updated today

    git clone https://github.com/TheColliery/CoalFace.git
  13. CorvinOS

    Skills

    Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

    Indexed GitHub, CorvinLabs 25 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/CorvinLabs/CorvinOS.git
  14. CoalWash

    Skills

    Memory washer/defragmenter for AI agent memory: class-B semantic wash (fidelity-gated, blocks any structured-token drop, snapshot+rollback) and class-A byte-identity session estate (ULTRA archive/restore, RE-TIER) - never semantic-edited. Cleans the FAT, never the MEAT. Slows memory-overhead growth; does not eliminate it. Zero-dependency.

    Indexed GitHub, TheColliery 14 ★Apache-2.0Updated today

    git clone https://github.com/TheColliery/CoalWash.git
  15. CoalTipple

    Skills

    Safe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated fable top rung. Not the cheapest router; the safest one inside Claude.

    Indexed GitHub, TheColliery 8 ★Apache-2.0Updated yesterday

    git clone https://github.com/TheColliery/CoalTipple.git
  16. deepcrew

    Skills

    🤿 The cheapest multi-agent workforce that is actually user-friendly: 7.7x more productive and 50x cheaper compared to your ultracode mode, an intelligent multi-agent swarm of Claude Code agents on DeepSeek or other providers, integrated with your own Claude Code or Codex.

    Stale GitHub, KuiyiGao 11 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/KuiyiGao/deepcrew.git
  17. Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.

    Stale GitHub, pvjbuilds 33 ★MITUpdated 15 days ago

    git clone https://github.com/pvjbuilds/delegate-router.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.