simantaturja/cccost-dashboard
Local, zero-setup dashboard for Claude Code token usage and cost — per project, client, model, and prompt, with an efficiency advisor.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit simantaturja/cccost-dashboard/.claude ./rig-cccost-dashboard # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit simantaturja/cccost-dashboard/.claude/skills/cccost-product-owner .claude/skills/cccost-product-owner $ npx degit simantaturja/cccost-dashboard/.claude/skills/issue-to-pr .claude/skills/issue-to-pr $ npx degit simantaturja/cccost-dashboard/.claude/skills/loop-design .claude/skills/loop-design $ npx degit simantaturja/cccost-dashboard/.claude/skills/loop-issue .claude/skills/loop-issue $ npx degit simantaturja/cccost-dashboard/.claude/skills/loop-pipeline .claude/skills/loop-pipeline $ npx degit simantaturja/cccost-dashboard/.claude/skills/loop-plan .claude/skills/loop-plan $ npx degit simantaturja/cccost-dashboard/.claude/skills/loop-watchdog .claude/skills/loop-watchdog $ npx degit simantaturja/cccost-dashboard/.claude/skills/release .claude/skills/release
$ curl -fsSL --create-dirs -o .claude/agents/loop-drafter.md https://raw.githubusercontent.com/simantaturja/cccost-dashboard/master/.claude/agents/loop-drafter.md $ curl -fsSL --create-dirs -o .claude/agents/loop-verifier.md https://raw.githubusercontent.com/simantaturja/cccost-dashboard/master/.claude/agents/loop-verifier.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(npm publish:*)",
"Bash(gh pr merge:*)",
"Bash(gh pr review:*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "in=$(cat); c=$(jq -r '.tool_input.command // \"\"' <<<\"$in\"); if printf '%s' \"$c\" | grep -Eq -- '(--add-label|--label)[ =][^ ]*loop:(go|build)'; then echo \"Applying loop:go or loop:build is a human gate (gate 1 / gate 2). Refusing.\" >&2; exit"
}
]
}
]
}
} Skills (8)
Subagents (2)
| loop-drafter | Implements ONE loop finding in a git worktree against explicit acceptance criteria. Runs unattended — no human will answer questions. Used by the loop-pipeline skill. |
| loop-verifier | Adversarially reviews a loop-produced diff, spec, or plan against AGENTS.md and the tests, and returns a verdict. Has no Edit or Write tool and never repairs what it judges. Used by the loop-pipeline |
Hooks (3)
| event | matcher | runs |
|---|---|---|
| Stop | * | npm run lint --silent || exit 2 |
| PostToolUse | Edit|Write | in=$(cat); f=$(jq -r '.tool_input.file_path // ""' <<<"$in"); case "$f" in */web/src/*) echo 'web/src changed — npm run test:ui must pass before this is done.' ;; esac; exit 0 |
| PreToolUse | Bash | in=$(cat); c=$(jq -r '.tool_input.command // ""' <<<"$in"); if printf '%s' "$c" | grep -Eq -- '(--add-label|--label)[ =][^ ]*loop:(go|build)'; then echo "Applying loop:go or loop:build is a human gate (gate 1 / gate 2). Refusing." >&2; exit |
Permissions
deny (3)
Bash(npm publish:*)
Bash(gh pr merge:*)
Bash(gh pr review:*)
ask (0)
—
allow (0)
—
Similar rigs
eugene1g/agent-safehouse
Sandbox your local AI agents so they can read/write only what they need
Minimalist 1.5k tok ·
jgravelle/jdocmunch-mcp
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
Pragmatist 18.0k tok ·
movieclaw/MovieClaw
Next-gen AI media server. One container replaces Sonarr, Radarr, Prowlarr, Bazarr, Jellyseerr and Jellyfin, with a web app, a native iPhone app, and an AI agent that gets things done. Free for personal use.
Minimalist 305 tok ·
mochow13/keen-code
A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MCPs, Subagents, Agent Skills, controllable tool output retention, hashline edits, and more.
Minimalist 342 tok ·