Paste This Into Claude Code, Never Run Out Of Tokens Again
Sharbel A.
308,834 views
Claude Code told me to come back in five hours, even though almost none of my usage came from what I actually typed. The real problem was hidden inside context, cache resets, tool output, MCP servers, subagents, and scheduled tasks.
In this video, I break down how Claude Code token consumption actually works, show the mistakes quietly burning through your limits, and give you a prompt that audits your own setup.
What’s covered:
0:00 Why Claude Code runs out of tokens
0:58 How context compounds on every message
1:52 Audit your Claude Code token usage
2:47 Fix 1: Clear between different jobs
4:32 Fix 2: Stop switching models mid-session
6:20 Fix 3: Filter massive tool output
7:39 Fix 4: Disable unused MCP servers
10:17 When subagents save tokens and when they waste them
12:28 Pick the right model before starting
12:55 The scheduled-task trap burning tokens overnight
14:39 Token-saving advice that does not work
16:24 How to monitor context, usage, cost, and burn rate
18:10 The complete token-saving system
19:03 Run the audit regularly
---
Paste this into Claude Code:
Audit this setup for token waste. Do not fix anything. Report only.
Use your shell and file tools to measure each item. If you cannot invoke slash
commands yourself, ask me to run /context and /usage and paste the output, then
continue.
1. MEMORY
Find every CLAUDE.md in scope: this project, parent directories, the user
level one, and anything pulled in with @imports. Report each file's size in
tokens. Flag any single file over 5k and any total over 10k.
2. TOOLS
List connected MCP servers and how many tools each exposes. State plainly
whether tool deferral is ACTIVE or NOT. Then check for a proxy or gateway
(ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, any gateway variable) and say so
loudly if you find one, because routing through a proxy silently turns
deferral off and nothing warns you.
3. MODEL
Report the current model and effort level and where each is set. Flag any
mode that changes model automatically during a session, because every
switch rebuilds the whole cache.
4. HOOKS
List any PreToolUse hooks that rewrite noisy commands to produce less
output. If there are none, say so, because unfiltered test and build output
lands in context verbatim and is re-sent for the rest of the session.
5. SUBAGENTS
List every agent file in the project and user agent directories. For each,
report whether it sets an explicit model in frontmatter or inherits the
main session's model.
6. SCHEDULED WORK
List every cron, scheduled task and background job with its interval.
Compare each interval against the prompt cache lifetime. Flag every one
whose interval is longer, because those miss cache on every single fire.
7. CACHE
Parse the newest session log under the projects directory. For every
assistant turn, sum usage.cache_read_input_tokens,
cache_creation_input_tokens, input_tokens and output_tokens. Report each as
a percentage of the total. Also report the context size on the first turn
and on the last turn.
Output one table, sorted by cost, highest first:
FINDING | SEVERITY | EVIDENCE | WHAT IT IS COSTING ME
Severity is RED, AMBER or GREEN. Evidence is a number or a file path, never an
adjective.
Then one final line: the single highest-leverage change I should make. One
line, nothing else.
Rules: measure, do not estimate. Write UNKNOWN rather than guessing. Change no
file and no setting.
---
Run the audit again whenever you add a plugin, MCP server, scheduled task, or major instruction file. Small configuration changes compound quickly.
Subscribe for more practical Claude Code, AI agent, and automation workflows.
20 Comments
1. Clear between jobs: Use `/clear` to reset the context base when starting a new task (2:47-4:25).
2. Maintain model consistency: Switching models or effort levels midsession forces a cache rebuild, which is highly expensive; set your model and effort at the start of a session (4:32-6:19).
3. Filter tool output: Use PreToolUse hooks to prevent verbose terminal or test output from flooding your context (6:20-7:39).
4. Manage MCP servers: Run `/mcp` to disable unused tools, ensuring that only necessary manuals are loaded (7:39-10:16).
5. Delegate wisely: Only use subagents when dealing with high-volume output that won't be needed again, and consider using Haiku to save tokens (10:17-12:28).
6. Review scheduled tasks: Ensure cron jobs or background tasks run at intervals that align with prompt cache lifetimes to avoid redundant full-context sends (12:55-14:39).
Subscribed of course!
Thanks so much!
Plus, your transitions by sliding on your chair, dude that’s clever. And it works. An analog wipe. Makes it much more watchable.
I am now going back to my laptop to try out your tips.
Liked the video. Subscribing!!
5-Stars, and I would definitely recommend/share this video with anyone I know who uses Claude Code.
Many thanks and God Bless.🙏🙏🙏
Anyway, pretty solid recommendations from first watch, I'll go look at the prompts. Pity it needs to be a screen grab rather than have the description link to a repo.
Paste This Into Claude Code, Never Run Out Of Tokens Again
Sharbel A.
308,834 views
Claude Code told me to come back in five hours, even though almost none of my usage came from what I actually typed. The real problem was hidden inside context, cache resets, tool output, MCP servers, subagents, and scheduled tasks.
In this video, I break down how Claude Code token consumption actually works, show the mistakes quietly burning through your limits, and give you a prompt that audits your own setup.
What’s covered:
0:00 Why Claude Code runs out of tokens
0:58 How context compounds on every message
1:52 Audit your Claude Code token usage
2:47 Fix 1: Clear between different jobs
4:32 Fix 2: Stop switching models mid-session
6:20 Fix 3: Filter massive tool output
7:39 Fix 4: Disable unused MCP servers
10:17 When subagents save tokens and when they waste them
12:28 Pick the right model before starting
12:55 The scheduled-task trap burning tokens overnight
14:39 Token-saving advice that does not work
16:24 How to monitor context, usage, cost, and burn rate
18:10 The complete token-saving system
19:03 Run the audit regularly
---
Paste this into Claude Code:
Audit this setup for token waste. Do not fix anything. Report only.
Use your shell and file tools to measure each item. If you cannot invoke slash
commands yourself, ask me to run /context and /usage and paste the output, then
continue.
1. MEMORY
Find every CLAUDE.md in scope: this project, parent directories, the user
level one, and anything pulled in with @imports. Report each file's size in
tokens. Flag any single file over 5k and any total over 10k.
2. TOOLS
List connected MCP servers and how many tools each exposes. State plainly
whether tool deferral is ACTIVE or NOT. Then check for a proxy or gateway
(ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, any gateway variable) and say so
loudly if you find one, because routing through a proxy silently turns
deferral off and nothing warns you.
3. MODEL
Report the current model and effort level and where each is set. Flag any
mode that changes model automatically during a session, because every
switch rebuilds the whole cache.
4. HOOKS
List any PreToolUse hooks that rewrite noisy commands to produce less
output. If there are none, say so, because unfiltered test and build output
lands in context verbatim and is re-sent for the rest of the session.
5. SUBAGENTS
List every agent file in the project and user agent directories. For each,
report whether it sets an explicit model in frontmatter or inherits the
main session's model.
6. SCHEDULED WORK
List every cron, scheduled task and background job with its interval.
Compare each interval against the prompt cache lifetime. Flag every one
whose interval is longer, because those miss cache on every single fire.
7. CACHE
Parse the newest session log under the projects directory. For every
assistant turn, sum usage.cache_read_input_tokens,
cache_creation_input_tokens, input_tokens and output_tokens. Report each as
a percentage of the total. Also report the context size on the first turn
and on the last turn.
Output one table, sorted by cost, highest first:
FINDING | SEVERITY | EVIDENCE | WHAT IT IS COSTING ME
Severity is RED, AMBER or GREEN. Evidence is a number or a file path, never an
adjective.
Then one final line: the single highest-leverage change I should make. One
line, nothing else.
Rules: measure, do not estimate. Write UNKNOWN rather than guessing. Change no
file and no setting.
---
Run the audit again whenever you add a plugin, MCP server, scheduled task, or major instruction file. Small configuration changes compound quickly.
Subscribe for more practical Claude Code, AI agent, and automation workflows.