By csbproserve
Claude Code usage reports and executive summaries: correlate spend with git commits, session history, COCOMO value, and hours saved; then turn it into a credible, executive-ready write-up. Supports multi-machine data collection.
Use when gathering Claude usage data from multiple development workstations (AVD, Linux jump host, etc.) to consolidate into a single portable bundle for report generation on one machine.
Use when the user needs to turn a Claude usage report (or their month's work) into an executive-ready summary for a named leader — quantifies hours saved credibly, discovers each workstream and its business value, and produces a prose write-up plus a one-page summary.
Use when the user wants a report correlating Claude Code spend with actual work output — git commits, session work, lines of code, and business value — broken down week over week.
Use when estimating the COCOMO development cost or hours saved for code committed by a specific author across multiple git repos, using scc at a given hourly rate.
A Claude Code plugin with four skills for generating usage reports that correlate Claude spend with actual work output — git commits, session history, COCOMO development value, and hours saved — and turning that into a credible, executive-ready summary.
claude-usage-collectCollects Claude session history from a workstation into a portable tarball. Use this on each machine (AVD, Linux jump host, local Mac) before running the report. Bundles are merged on the reporting workstation using CLAUDE_CONFIG_DIR.
claude-usage-reportBuilds the weekly report by correlating:
Output: a dated markdown file with per-week sections, a summary table, and optional COCOMO value.
scc-cocomoRuns scc against files committed by a specific author across multiple repos to produce a COCOMO development cost estimate at a given hourly rate. Reports estimated cost, hours saved, and ROI ratio vs actual Claude spend.
claude-usage-exec-summaryTurns the detailed report into an executive-ready summary for a named leader (CEO, CFO, CTO, board). Discovers and quantifies your role (and remembers it), walks you through each workstream and its real business value, estimates hours saved via a credible team-equivalent method, and produces both a prose write-up and a one-page summary. Bakes in the guardrails that keep the numbers believable — no COCOMO vanity multiples, no jargon, verified project status, spend never framed as a credential.
Output: a dated markdown file with a prose write-up addressed to the executive plus a skimmable one-page summary.
ccusage — npm install -g ccusage (required for usage-report)scc — brew install scc or go install github.com/boyter/scc/v3@latest (required for scc-cocomo only)jq — brew install jqThe skills that need these tools check for them and print install instructions automatically before running. claude-usage-exec-summary needs no extra tools — it consumes the report's output.
# Add the marketplace (once)
claude plugin marketplace add https://github.com/csbproserve/claude-usage-toolkit
# Then install the plugin
claude plugin install claude-usage-toolkit
Each workstation Reporting workstation
───────────────── ─────────────────────
claude-usage-collect ──tarball──► merge + ccusage + claude-usage-report
See the claude-usage-collect skill for the collect/merge scripts.
claude-usage-collect (optional, multi-machine)
↓
claude-usage-report (main report)
↓
scc-cocomo (optional, COCOMO value estimate)
↓
claude-usage-exec-summary (optional, executive-ready write-up)
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub csbproserve/claude-usage-toolkit --plugin claude-usage-toolkitComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Payload Development plugin - covers collections, fields, hooks, access control, plugins, and database adapters.