By centminmod
Analyze Claude Code session token usage, cost, and cache metrics from JSONL logs. Identify waste patterns, group turns into semantic tasks with worth-it verdicts, and export reports in multiple formats including HTML with cost timelines and cache-break badges.
Audit a session-metrics JSON export for token-usage waste and produce a plain-English findings report. Trigger when the user runs /audit-session-metrics, when session-metrics suggests an audit after an HTML export, or when the user asks to audit / review / find waste in a saved session-metrics JSON. Two modes: "quick" (ratios + cache health + top expensive turns/sessions) and "detailed" (adds CLAUDE.md / settings / re-read scan). Supports session, project, and instance JSON scopes. Args: $ARGUMENTS[0] = quick|detailed, $ARGUMENTS[1] = path to a session-metrics JSON export.
Tally Claude Code session token usage and cost estimates from the raw JSONL conversation log. Trigger when the user asks about session cost, token usage, API spend, cache hit rate, input/output tokens, or wants a breakdown of how much a Claude Code session has cost. Also trigger for "how much have we spent", "show me token usage", "session summary", "cost so far", or any request to analyse or display per-turn metrics from the current or a past session. Do NOT auto-dispatch compare mode (--compare / --compare-prep / --compare-run / --count-tokens-only) from natural-language phrases. The skill body uses $ARGUMENTS[0] as the dispatch key — if the first positional argument is not literally "compare", "compare-prep", "compare-run", or "count-tokens", route to the default single-session report.
Group a session-metrics session's turns into higher-level SEMANTIC TASKS ("what was I actually trying to do") and render a Tasks companion page (*_tasks.html + *_tasks.md) with a worth-it / mixed / likely-waste verdict per task. Trigger when the user runs /task-breakdown, when session-metrics suggests a task breakdown after a JSON export, or when the user asks to "group my turns into tasks", "what tasks did this session cover", "which work was worth it vs wasted", or "break this session into tasks". Consumes the deterministic per-request breakdown (request_units) from a session-metrics JSON export — it never re-derives cost or token numbers. Args: $ARGUMENTS[0] = path to a session-metrics JSON export (optional; if omitted, generate one first).
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A personal Claude Code plugin marketplace. Each plugin is an independent, standalone unit that can be installed into any Claude Code project with a single command.
Claude Code's plugin system supports multiple plugins per marketplace and handles install + update lifecycle automatically. See the official plugin-marketplaces docs for the broader ecosystem.
Add this marketplace once, then install any plugin from it:
Run
/plugincommands inside the Claude Code terminal CLI (claudein your shell). They are not recognised in the desktop app, claude.ai/code, or IDE extensions — you'll see "/plugin isn't a recognized command here" if you try. Installed plugins then work from every surface; only the install step requires the CLI.
/plugin marketplace add centminmod/claude-plugins
| Plugin | Description | Install |
|---|---|---|
session-metrics | Per-turn token, cost, and cache metrics for Claude Code sessions. Multi-format export (text/JSON/CSV/MD/HTML) with 5-hour session blocks, weekly roll-up, hour-of-day punchcard, and pluggable chart libraries. | /plugin install session-metrics@centminmod |
More plugins coming.
session-metricsBackground articles by the author on what the skill does and what it surfaces in practice:
Plugin skills are namespaced as plugin-name:skill-name — for example
/session-metrics:session-metrics. In practice you rarely type that form:
each skill declares natural-language triggers in its SKILL.md, so Claude
Code auto-invokes the right one when you ask something like "how much has
this session cost?".
LICENSE).plugins/*/ carries its own LICENSE and may bundle
third-party assets under their upstream licences. For session-metrics
specifically, the default Highcharts renderer ships under a
non-commercial-free licence — commercial use requires a paid Highsoft
licence. MIT-licensed alternatives (uPlot, Chart.js) are selectable via
the --chart-lib flag. See
plugins/session-metrics/skills/session-metrics/scripts/vendor/charts/README.md
for per-library LICENSE.txt files.This is a personal marketplace — issues and pull requests are welcome but plugin additions are curated. Feel free to open an issue to discuss bundling something new.
npx claudepluginhub centminmod/claude-plugins --plugin session-metricsText-to-speech for Claude Code using Kokoro-FastAPI with voice blending, streaming, and comprehensive format support
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Plugin-safe Claude Code distribution of Agentic Awesome Skills with 1,933 supported skills.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,884 supported skills.
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).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques