Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
hush
PromptsQuieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
git clone https://github.com/V-Songbird/hush.git -
paritok-4b-v1
Tools & appsNon-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
git clone https://github.com/Paritok-official/paritok-4b-v1.git -
opus-tuner-claude-skill
SkillsCost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.
git clone https://github.com/YahyaLendani/opus-tuner-claude-skill.git -
Chisle
SkillsCut 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.
git clone https://github.com/JayPokale/Chisle.git -
LAP
Tools & appsYour agents are guessing at APIs. Give them the actual Agent-Native spec. 1500+ API's Ready To-Use skills, Compile any API spec into a lean, agent-native format. 10× smaller. OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman.
git clone https://github.com/Lap-Platform/LAP.git -
context-attachment-manager
MCP serversTurn Codex and Claude Code into your AI assistant director. Pair them with your favorite image-generation tools, keep image-heavy chats lightweight, and find the right image from a rough description—even after repeated context compaction.
git clone https://github.com/chipfighter/context-attachment-manager.git -
claude-handoff-revive
SkillsResume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.
git clone https://github.com/sofumel/claude-handoff-revive.git -
honey-for-devs
PromptsHoney (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.
git clone https://github.com/Green-PT/honey-for-devs.git -
ripwire
MCP serversThe ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.
git clone https://github.com/redhat-et/ripwire.git -
Agent-Blackbox
Tools & appsLocal-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
git clone https://github.com/TaewoooPark/Agent-Blackbox.git -
Token Diet
MCP serversLLM token optimization gateway implementing semantic pruning.
-
awesome-ai-tokenomics
Docs & tutorialsA curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents.
git clone https://github.com/QuesmaOrg/awesome-ai-tokenomics.git -
rote
SkillsCompile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
git clone https://github.com/trevhud/rote.git -
agent-token-saver
SkillsTypeScript/Bun tools for coding agents. Run checks once, keep complete evidence, and test output filters against task-specific requirements. No runtime packages.
git clone https://github.com/Supersynergy/agent-token-saver.git -
kyber-weave
SkillsAgentic 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.
git clone https://github.com/dpalfery/kyber-weave.git -
logic-server
MCP serversAgent reasoning, memory, and token-optimized context for AI applications.
nocturnusai-mcp@0.3.11 -
three-man-team
SkillsA 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.
git clone https://github.com/russelleNVy/three-man-team.git -
aiwg
SkillsReusable 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.
git clone https://github.com/jmagly/aiwg.git -
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.
git clone https://github.com/2233admin/cli2skill.git -
gcf
MCP serversThe AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1 Stable.
git clone https://github.com/blackwell-systems/gcf.git -
CoalFace
SkillsFan-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.
git clone https://github.com/TheColliery/CoalFace.git -
wordpress-mcp
MCP serversMulti-site WordPress MCP server - 249 tools, token-optimized responses
@cavort-it-systems/wordpress-mcp@3.14.1 -
llmtrim
PromptsLocal proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
git clone https://github.com/fkiene/llmtrim.git -
clickup-mcp
MCP serversLightweight ClickUp MCP server - 37 tools, token-optimized (95% smaller responses)
@cavort-it-systems/clickup-mcp@1.1.0
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.