skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
egorfedorov/claude-context-optimizer261 installs

cco

In Claude Code: what this session costs and where the tokens go, plus the tools to cut it — /cco for the board, /cco audit, /cco task, /cco pack and more. Use when the user asks about session cost, context size, savings, or wants a task tracked across /compact.

How do I install this agent skill?

npx skills add https://github.com/egorfedorov/claude-context-optimizer --skill cco
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubwarn

    This skill provides a comprehensive suite of tools for tracking and optimizing token usage in Claude Code sessions. It executes several local Node.js scripts and accesses sensitive session transcripts and configuration files in the user's home directory.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Context Optimizer

Needs Claude Code (or Cowork on your computer): this runs the plugin's local scripts. If node or ${CLAUDE_PLUGIN_ROOT} isn't available, as in claude.ai chat, don't try to run anything. Say so in one line and offer the fresh-start or token-check skill instead.

Arguments: $ARGUMENTS. The first word is the command; the rest are its <args>. No command means board. help, or a command not in the table, means: print the table below as a short menu and stop.

For a command, read its instructions in ${CLAUDE_PLUGIN_ROOT}/skills/cco/commands/<command>.md and follow them. Those files write the plugin's path as ${CLAUDE_PLUGIN_ROOT}: use ${CLAUDE_PLUGIN_ROOT} in its place, and the user's <args> where they say <args>. When the user typed only a command that just runs its script, run the script from the table directly and skip reading the file.

See where the tokens go

CommandWhat it showsScript
(none) / boardThis session: budget, $ spent, saved, waste, active task, next actionsnode ${CLAUDE_PLUGIN_ROOT}/src/dashboard.js board
auditYour real transcripts: where the money went and what CCO savednode ${CLAUDE_PLUGIN_ROOT}/src/audit.js <args>
wrappedA recap of your last week: spend, busiest day, priciest projects, one tipnode ${CLAUDE_PLUGIN_ROOT}/src/wrapped.js <args>
reportToken ROI across all tracked sessionsnode ${CLAUDE_PLUGIN_ROOT}/src/report.js full
roiMonthly savings by modelnode ${CLAUDE_PLUGIN_ROOT}/src/roi.js
digestEfficiency score and trend for the last N daysnode ${CLAUDE_PLUGIN_ROOT}/src/digest.js <args>
replayRecent session summariesnode ${CLAUDE_PLUGIN_ROOT}/src/replay.js <args>
toolsWhat each tool really costs in tokensnode ${CLAUDE_PLUGIN_ROOT}/src/tool-costs.js
overheadThe fixed context every session starts withnode ${CLAUDE_PLUGIN_ROOT}/src/overhead.js

Spend less

CommandWhat it does
orchestrate <task>Do a task with Haiku subagents doing the reading and test runs
taskTrack a task's cost and keep its state across /compact
pack <task>The files a task needs, with line ranges, before reading anything
anatomyA compact map of the project
gitContext suggestions from the git working tree
claudemdFind bloat in CLAUDE.md
coachGrade the last prompt and sharpen it
shield.contextignore rules from what was never used
templatesSaved context sets for recurring tasks

Settings and data

CommandWhat it does
configTune thresholds (re-read warnings, cache staleness, coach)
budgetContext budget and auto-compact settings
exportSave a report as Markdown or an offline HTML page
patternsShare learned file patterns with a team
cleanPrune or reset tracked data
doctorCheck the install end to end

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/egorfedorov/claude-context-optimizer/cco">View cco on skillZs</a>