Show HN: Tokenscope – see what your Claude Code session cost

wartzarbee2 pts0 comments

GitHub - wartzar-bee/tokenscope: See what your AI-coding session actually cost — and what is eating your context. Local, read-only CLI for Claude Code. · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

wartzar-bee

tokenscope

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>1 Commit<br>1 Commit

bin

bin

src

src

test

test

.gitignore

.gitignore

README.md

README.md

launch.md

launch.md

package.json

package.json

View all files

Repository files navigation

tokenscope ⏣

See what your AI-coding session actually cost — and what's eating your context.<br>A local, read-only CLI that parses your Claude Code session logs and shows where the money goes: model output vs. context being re-sent every turn (the hidden 60%+ of most bills).

$ npx tokenscope

tokenscope ⏣ latest session<br>──────────────────────────────────────────────────────<br>Total cost $868.84 over 967 model turns

Where the money went<br>output (model writing) ████░░░░░░░░░░░░░░░░░░░░ 16% $137.24<br>cache read (re-sent ctx) ████████████████░░░░░░░░ 66% $577.59<br>cache write (new ctx) ████░░░░░░░░░░░░░░░░░░░░ 18% $153.67

Context size per turn (peak 822k · avg 404k · now 822k tokens)<br>▁▁▁▁▁▂▂▂▂▂▂▂▃▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▆▆▆▆▇▇▇▇▇▇█

Insights<br>• Re-sent (cached) context cost $577.59 (66% of spend) — context re-read every turn.<br>• Peak context ~822k tokens — /compact or a fresh session would cut per-turn cost.<br>• Only 16% of spend is the model's actual output.

(A real session, default Opus pricing. Your numbers will differ — prices are overridable.)

Why

Agentic coding (Claude Code, etc.) produces surprise bills, and the cause is mundane: as a session grows, the whole context is re-sent every turn , so cost balloons even when the model writes little. Existing dashboards show totals; tokenscope shows the attribution — output vs. cache-read vs. cache-write vs. fresh input, the per-turn context-growth curve, cost by model, subagent spend, and which tools fill your context — with concrete "trim this" insights.

Install / run

# a specific session .jsonl<br>npx tokenscope --json # machine-readable">npx tokenscope # your most recent Claude Code session<br>npx tokenscope --all # aggregate every session<br>npx tokenscope # a specific session .jsonl<br>npx tokenscope --json # machine-readable

Reads ~/.claude/projects/**/*.jsonl. Read-only, local, no network, no telemetry — open the source; nothing leaves your machine.

Pricing

Uses documented default prices (Anthropic cache multipliers: write 1.25×/2×, read 0.1× of input). Verify and override for your exact model/tier via ./.tokenscope.json:

{ "pricing": { "claude-opus-4": { "in": 15, "out": 75 } } }

Unknown models are flagged (never silently counted as $0). Token counts are read straight from the logs; cost = those counts × the prices shown.

Status / roadmap

v0.1: Claude Code session cost + context attribution + insights. 20/20 unit tests on the cost math (npm test).

Next (evidence-driven): per-tool/-file token attribution; daily/budget alerts; a --watch live meter; OpenAI/Codex log support.

MIT. Not affiliated with Anthropic.

About

See what your AI-coding session actually cost — and what is eating your context. Local, read-only CLI for Claude Code.

Topics

cli

developer-tools

claude

cost-analysis

anthropic

token-usage

llm-cost

claude-code

agentic-coding

ai-cost

Resources

Readme

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

stars

Watchers

watching

Forks

forks

Report repository

Releases

tokenscope v0.1.0

Latest

May 28, 2026

Packages

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

JavaScript<br>100.0%

You can’t perform that action at this time.

session cost tokenscope context claude read

Related Articles