cco
Skill127 starsChanged 5 months agoMITView on GitHub
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.
In this repository5 other files it gives its agents.
- doc-digestSkill
- fresh-startSkill
- project-contextSkill
- sharpen-promptSkill
- token-checkSkill
The file
Files
Context Optimizer
Needs Claude Code (or Cowork on your computer): this runs the plugin's local scripts. If
nodeor${CLAUDE_PLUGIN_ROOT}isn't available, as in claude.ai chat, don't try to run anything. Say so in one line and offer thefresh-startortoken-checkskill 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
| Command | What it shows | Script |
(none) / board | This session: budget, $ spent, saved, waste, active task, next actions | node ${CLAUDE_PLUGIN_ROOT}/src/dashboard.js board |
audit | Your real transcripts: where the money went and what CCO saved | node ${CLAUDE_PLUGIN_ROOT}/src/audit.js <args> |
wrapped | A recap of your last week: spend, busiest day, priciest projects, one tip | node ${CLAUDE_PLUGIN_ROOT}/src/wrapped.js <args> |
report | Token ROI across all tracked sessions | node ${CLAUDE_PLUGIN_ROOT}/src/report.js full |
roi | Monthly savings by model | node ${CLAUDE_PLUGIN_ROOT}/src/roi.js |
digest | Efficiency score and trend for the last N days | node ${CLAUDE_PLUGIN_ROOT}/src/digest.js <args> |
replay | Recent session summaries | node ${CLAUDE_PLUGIN_ROOT}/src/replay.js <args> |
tools | What each tool really costs in tokens | node ${CLAUDE_PLUGIN_ROOT}/src/tool-costs.js |
overhead | The fixed context every session starts with | node ${CLAUDE_PLUGIN_ROOT}/src/overhead.js |
Spend less
| Command | What it does |
orchestrate <task> | Do a task with Haiku subagents doing the reading and test runs |
task | Track a task's cost and keep its state across /compact |
pack <task> | The files a task needs, with line ranges, before reading anything |
anatomy | A compact map of the project |
git | Context suggestions from the git working tree |
claudemd | Find bloat in CLAUDE.md |
coach | Grade the last prompt and sharpen it |
shield | .contextignore rules from what was never used |
templates | Saved context sets for recurring tasks |
Settings and data
| Command | What it does |
config | Tune thresholds (re-read warnings, cache staleness, coach) |
budget | Context budget and auto-compact settings |
export | Save a report as Markdown or an offline HTML page |
patterns | Share learned file patterns with a team |
clean | Prune or reset tracked data |
doctor | Check the install end to end |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.