Works with the AI Agents you already use
Slim Context
A zero-dependency, non-destructive Claude Code skill that slashes token context burn by 30–50% by safely flattening heavy repository noise into clean 1-line interface summaries.
Free
slim-context
Example session with this skill installed
My conversation context window is completely full and the session is getting sluggish. Can you look at this large monorepo workspace and optimize it so I stop running out of tokens?
- Read your context and instructions
- Compiled the slim-context
📉 Estimated Tokens Saved: 41%
🗑️ Dropped from Active Focus:
• node_modules/** → collapsed into 1-line interface stubs for 12 core imported packages.
• build-debug.log → 266 lines of webpack compilation spam compressed to a single summary line status.
• coverage/lcov-report/** → temporary build artifacts excluded from active focus.
• dist/**/*.map → source maps removed (zero feature edit impact).
💡 Retained Architecture Map:
The current branch workspace focuses heavily on src/auth/session.ts and src/middleware/token.ts, which remain fully loaded in memory. Public interface signatures for database pools and encryption utilities are cleanly preserved as high-signal one-liners.
🧹
Tip: Your total conversation token history is long. Run the native /compact command right now to flush stale memory loops and lock in these performance gains.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop paying the Claude Code Token Tax!
Modern repositories are flooded with verbose build logs, massive npm/yarn dependency dumps, and runaway test coverage files. Claude Code blindly loads these files into its active focus window, draining your 5-hour quota and weekly limits in minutes.
slim-context turns your AI session into a disciplined context optimizer:
- 🔍 Context Auditing: Automatically inventories loaded text noise.
- 🧬 Interface Preservation: Replaces large, non-essential dependencies and files with 1–2 line summaries of their public interface signatures.
- ⚠️ Prime Directive: 100% non-destructive. It only manages what the AI session keeps in active memory—disk contents are NEVER altered.
- 🧹 Hygiene Prompting: Recommends when to trigger native compaction loops to lock in token reductions.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
Only affects active session attention, not files on disk. Requires manual trigger or specific threshold keywords to activate.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 9 days ago
- Free with an Agensi account
- Software
- Claude Code
Permissions
Requires read access to inventory active context files and trees. Non-destructive by design; never modifies any files on disk.