Usage & cost
370 mods. Tokens, spend and rate limits at a glance.
-
big-read-guard
1.1.1
Stops full reads of huge files and nudges toward offset/limit or grep.
Plagemes in Usage & cost, updated
1
-
output-trimmer
1.0.0
Trims huge command outputs to head, tail and error lines before they flood the context.
Plagemes in Usage & cost, updated
1
-
daily-spend
1.1.2
Tracks spend per day and week across sessions with a /spend report.
Plagemes in Usage & cost, updated
1
-
model-advisor
1.1.1
Suggests a cheaper model when your prompt is simple, and a stronger one when it is hard.
Plagemes in Usage & cost, updated
1
-
compact-coach
1.1.1
Suggests /compact at natural breakpoints, before the context gets tight.
Plagemes in Usage & cost, updated
1
-
session-stats
1.1.2
/session-stats shows a dashboard of turns, tools, tokens, cost, duration and files.
Plagemes in Usage & cost, updated
1
-
token-sparkline
1.1.1
A sparkline of tokens per turn right above the prompt.
Plagemes in Usage & cost, updated
1
-
cloud-cost-warn
1.1.1
Warns before commands that create expensive cloud resources like GPU instances or large databases.
Plagemes in Usage & cost, updated
1
-
query-result-cap
1.0.0
Adds a LIMIT to ad-hoc SELECTs Claude runs in psql, mysql or sqlite so results don't flood the context.
Plagemes in Usage & cost, updated
1
-
csv-peek
1.0.1
/peek shows a CSV or JSONL file's columns, sample rows and inferred types without reading the whole file.
Plagemes in Usage & cost, updated
1
-
css-token-guard
1.1.1
Flags hard-coded hex colors and pixel values where your design tokens should be used.
Plagemes in Usage & cost, updated
1
-
rate-limit-guard
1.1.1
Stops Claude from hammering external APIs with curl loops.
Plagemes in Usage & cost, updated
1
-
jwt-decode
1.0.1
/jwt decodes a JSON Web Token locally — header, claims, expiry — without sending it anywhere.
Plagemes in Usage & cost, updated
1
-
pii-in-logs
1.1.1
Flags log statements that print emails, passwords, tokens or other personal data.
Plagemes in Usage & cost, updated
1
-
crypto-guard
1.1.1
Flags weak cryptography: MD5 or SHA1 for passwords, Math.random for tokens, ECB mode, hard-coded IVs.
Plagemes in Usage & cost, updated
1
-
smart-router
1.0.3
Routes every subagent to the right model for the task's difficulty, runs independent work in parallel and starts workflows when a job needs one.
Plagemes in Usage & cost, updated
1
-
context-optimizer
1.0.2
Keeps the context lean automatically: trims noise, picks the right moment to compact and shows the tokens it saved.
Plagemes in Usage & cost, updated
1
-
mission-control
1.0.2
One dashboard for every Claude session on your machine: what each is doing, cost, blockers, with pause and priorities.
Plagemes in Usage & cost, updated
1
-
session-meter
0.1.0
Band above the prompt showing context-window fill and prompt-cache time left as bars
KingoBoiii in Usage & cost, updated
1
-
usage-limits
0.6.0
Consumo de tokens, custo, previsão dos limites de 5h e semanal e recomendação de modelo
Kevin Medeiros in Usage & cost, updated
1
-
context-meter
0.6.0
Always-on context window meter above the prompt, with usage limits (terminal and desktop app)
Ronny Zimmermann in Usage & cost, updated
1
-
context-meter
0.2.0
A band above the prompt with what fills the context window, by category, a countdown to when the prompt cache expires, and a Compact button
Chien Vu Minh in Usage & cost, updated
1
-
usage-meter
0.3.0
Minimal band: model, context tokens and estimated session cost, coloured by context fill
KingMichaelPark in Usage & cost, updated
1
-
model-router
0.3.0
Routes each turn to the cheapest model + effort that fits the task (Haiku 5.5 → Sonnet 5.5 → Opus 5.5 → Fable 5.1) and shows the ladder in a side pane.
Troy Lorents in Usage & cost, updated
1
-
burn-rate
0.1.0
A terminal cost dashboard (/burn): spend by day, project, model, activity, tools, shell commands and MCP servers, read from your local Claude Code transcripts and estimated at list price.
Troy Lorents in Usage & cost, updated
1
-
secret-scrubber
0.1.0
Redacts API keys, tokens, private keys and .env secrets from tool output before the transcript stores it and before the model reads it.
Troy Lorents in Usage & cost, updated
1
-
usage-meter
0.1.0
Shows plan rate-limit usage, session cost, context fill and a per-task token estimate above the prompt
Rain Guo in Usage & cost, updated
1
-
usage-bar
0.1.0
Interactive band above the prompt: context fill, 5-hour and 7-day plan limits with resets, session cost, and a progress row for any subagents.
satyamk4517 in Usage & cost, updated
1
-
tool-visibility-controller
0.2.0
Claude Code plugin for per-agent tool visibility — hide and refuse subagents, skills, MCP and built-in tools per loop
Reza · Professor in Usage & cost, updated
1
-
clawd-minecraft
1.0.1
Usage tracker drawn as a block-game HUD: hearts and armor for the 7-day limit, XP bar for the 5-hour limit, hunger for the context window, and a Clawd that walks beside it
Abdullah Sultan in Usage & cost, updated
1