Furl Ctx — AI skill for Claude Code
Context compression for AI agents — cut token usage costs with retrievable CCR compression.
How to install Furl Ctx
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open omar-y-abdi/furl-ctx and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Furl Ctx does
Context compression for AI agents — cut token usage costs with retrievable CCR compression. Rust core + Python API, Claude Code & Codex plugin, MCP server. PyPI: furl-ctx
Alternatives in AI
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
- Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★
README
███████╗██╗ ██╗██████╗ ██╗ ██╔════╝██║ ██║██╔══██╗██║ █████╗ ██║ ██║██████╔╝██║ ██╔══╝ ██║ ██║██╔══██╗██║ ██║ ╚██████╔╝██║ ██║███████╗ ╚═╝ ╚═════╝ ╚═╝ ╚═╝╚══════╝ The context compression layer for AI agents![]()
furl-ctx
**Reversible context compression for AI agents.** furl-ctx shrinks large tool outputs, logs, web fetches, and RAG chunks before they fill your agent's context window, and keeps every original byte retrievable on demand. Think prompt compression and context pruning for token optimization, without losing data. CCR, short for Compress-Cache-Retrieve, is the core: compression where every dropped byte stays retrievable.
0–54% token savings on real high-entropy content · reaching 95% on repetitive logs/fixtures (honest read)
Claude Code + Codex plugins · MCP server usable by any MCP host · Reversible compression
Install · Proof · Library · Community
**What works today:** Claude Code gets the MCP tools, skill, and automatic compression hooks. Codex gets the same MCP tools and retrieval-aware skill; use `furl_compress` on demand because Codex plugins do not yet expose Furl's output-replacement hook. Automatic hands-off compression works on Claude Code 2.1.163 and newer: the PostToolUse hook mirrors each replacement to the tool's output shape, so the harness honors it, verified live by both external audits on
Related Skills
Cost Optimizer
git clone https://github.com/fullstackcrew-alpha/skill-cost-optimizer Save 60-80% on AI token costs with smart
Distil
Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewri
Cc Token Status
new macOS menu bar dashboard for Claude Code. Shows plan usage limits, costs, tokens, trends, model breakdown,
Syrtis Windows
Windows port of TokenBar — a tray monitor for AI coding-agent token usage, cost, and subscription quota. WinUI
Ham
(HAM) Memory system for AI coding agents. Cut token usage by 80% by scoping context to directories.
Smart Context Delegation
Cut coding-agent token usage by ~90%: a PreToolUse hook blocks large file reads; bulk-read/code-write delegate
Related Agents
API Cost Scanner
Scans codebase for AI/API cost optimization opportunities including model usage, token estimates, caching stra
Stats Analyzer
Analyzes ~/.claude/stats-cache.json and history.jsonl to produce a concise usage report with model token break
Codexcw Expert
Use for questions about working in or with the codexcw monorepo — its polyglot layout, the five-language API (