Works with the AI Agents you already use
Context Rent: What Eats Your Token Budget
On a real 192-turn Claude Code session, **96% of all tokens were context being re-read**, and output was under 1%.
Free
Context Rent: What Eats Your Token Budget
Example session with this skill installed
I keep hitting my Claude Code usage limit by mid-afternoon. What is eating my tokens in this project, and what should I change?
- Read your context and instructions
- Compiled the context rent
Summary
This is the real report from the Claude Code session that built a Dart payments package (192 turns).
96% of all tokens were context being re-read; output was under 1%. Three causes account for most of it.
Where the tokens went
| tokens | share | |
|---|---|---|
| Context re-read from cache | 49.1M | 96% |
| Context written to cache | 1.7M | 3% |
| Output (incl. thinking) | 129k | <1% |
What filled the context (size × turns it stayed)
| Source | calls | raw | carried |
|---|---|---|---|
| screenshots | 118 | 33k | 4.0M |
| shell output | 46 | 15k | 1.1M |
| other MCP tools | 76 | 9.1k | 1.1M |
| web pages | 42 | 15k | 836k |
| file reads | 2 | 2.0k | 306k |
Top causes
1. One long session with a large context (~17M tokens). 192 turns, average context ~265k. Every turn re-sent all of it.
→ One task per session; run /compact at a natural break instead of waiting for auto-compaction (790k → 29k tokens, once).
2. 36 screenshots stayed in context (~1.8M tokens). Browser screenshots were ~19k tokens raw but were carried for 2.7M.
→ Read pages as text (read_page / get_page_text) and take one screenshot only to check layout, at a reduced scale.
3. The prompt cache expired 6 times during breaks (~1.4M tokens). After pauses of 2 to 12 hours, ~230k tokens of context were written again each time.
→ After a long break on a big context, run /compact or start a fresh session with a short summary.
Suggested CLAUDE.md section
## Context budget
- Prefer reading pages as text; take a screenshot only to verify layout, at a reduced scale.
Next steps
Shall I add this section to CLAUDE.md? For the next big task, I suggest starting a new session and compacting at each milestone.
Connects securely to your tools. The creator never sees your data.
About this skill
Why your usage limit runs out
An agent sends its whole context again on every turn. On a real 192-turn Claude Code session, 96% of all tokens were context being re-read, and output was under 1%. So what matters is what sits in your context, and for how long.
A 2,000-token screenshot that stays for 100 turns costs 200,000 tokens. Context Rent charges every tool result for exactly that (size × turns it stayed in context) and turns the biggest rent-payers into fixes.
What it finds
| Finding | Fix it suggests |
|---|---|
| Long sessions with a big context | One task per session, /compact at task boundaries |
| Screenshots kept in context | Read pages as text, one screenshot per batch |
| Whole-file reads | Grep first, read a range |
| The same file read 3+ times | Edit from what is already in context |
| Noisy test/build/install output | Quiet flags, | tail, with the exact command named |
| Prompt cache expired during breaks | /compact or start fresh after a long pause |
| Large CLAUDE.md / AGENTS.md | Keep rules, move reference material out |
| MCP servers configured but never used | Remove them |
| Auto-compaction | Compact earlier |
It also writes a ready-to-paste Context budget section for CLAUDE.md / AGENTS.md.
How the agent uses it
- Runs the bundled zero-dependency Node script on your local logs (
~/.claude/projects,~/.codex/sessions). - Explains the shape of your usage and the top three causes, with numbers.
- Applies only the fixes you approve: CLAUDE.md lines, a trimmed instruction file, removing unused MCP servers.
Privacy
Runs offline. Reports contain sizes and short labels only (a file path, the start of a command), with API keys and tokens masked. Your prompts, code and command output never appear in the output.
Open source (MIT): https://github.com/MBotirjonDev/context-rent
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.
Requires local access to Claude Code or Codex CLI session logs. Estimates sizes at ~4 chars per token. Read-only until user approves config edits.
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
Git