Analytics and metrics

26,950 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

nateherkai/token-dashboard

Instructions file

Instructions for nateherkai/token-dashboard, covering claude.md, project overview, status, architecture and data source.

not rated 685 +2 4mo ago A 787 tokens original MIT

agentacct-workflow

122

mikehasa/agentacct

Skill Claude CodeCodex

Use when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.

not rated 698 yesterday A 40 tokens original MIT

openmobius-skill

123

MobiusQuant/OpenMobius-skill

Skill Claude CodeCodex

Provides multi-school trading Q&A, chart/OHLCV analysis, annotation, and fresh-market workflows covering ICT/SMC, ChanLun, Wyckoff, Price Action, Order Flow, VSA, and Elliott Wave. Use for trading concepts; capability-discovery questions about available analysis lenses, Schools, models, modes, or data sources…

not rated 673 +7 changed today A 151 tokens original Apache-2.0

world-cup-predictor

124

mikobinbin/2026-world-cup-predictor

Skill Claude CodeCodex

A system for predicting the 2026 men's football World Cup champion using player development, team Elo ratings, and additional non-sporting factors.

not rated 663 +1 1mo ago A 61 tokens

PaulDuvall/ai-development-patterns

Skill Claude CodeCodex

Run or plan this repository's pattern-adoption evidence evaluation locally with signed-in Codex agents. Use when asked to refresh stale evidence, assess stable or exploratory patterns, evaluate one or all catalog patterns, discover possible new patterns, or prepare a reviewable evidence PR without model-backed GitHub…

not rated 649 +4 yesterday A 68 tokens original MIT

wx-favorites-report

126

zhuyansen/wx-favorites-report

Skill Claude CodeCodex

A workflow that decrypts and reads WeChat’s local Favorites database, then creates an interactive HTML report. WeChat is a messaging app whose saved items can include collected content.

not rated 640 4mo ago A 81 tokens

abuse-hunter

127

nexu-io/harness-engineering-guide

Skill Claude CodeCodex

Detect and investigate bulk registration abuse on SaaS platforms. Given access to a user database (or exported CSV/JSON), run a multi-dimensional anomaly analysis — email domain clustering, registration tempo, UA fingerprinting, session structure, usage patterns, and credit consumption — to produce a scored abuse…

not rated 635 +10 4mo ago A 86 tokens original MIT

1688-item-selection

128

next-1688/1688-item-select

Skill Claude CodeCodex

A tool for selecting priority products from 1688, a Chinese wholesale marketplace. It scores products across five areas and groups them into S, A, B, or C priority levels.

not rated 628 +1 3mo ago A 112 tokens

flags-sdk

129

vercel/flags

Skill Claude CodeCodex ✓ vendor

Set up and use feature flags and A/B tests with the Flags SDK (flags npm package) and Vercel Flags. Use when installing or configuring the SDK, adding a new or existing flag, wiring vercelAdapter (OIDC or SDK keys), declaring flags with flag(), using the vercel flags CLI (create, inspect, list, enable, disable, set…

not rated 620 +4 changed yesterday A 258 tokens original MIT

mingli30119/stock-analysis

Skill Claude CodeCodex

A stock-research workflow that collects data from more than 30 sources, analyzes a stock’s business and market data, and creates Markdown and interactive HTML reports. It also supports refreshing existing reports with newer data.

not rated 620 +1 3mo ago A 91 tokens original MIT

marmot

131

marmotdata/marmot

MCP server Claude CodeCodexCursor +2

Open-source data catalog. Search assets, explore lineage, and find ownership. Remote server at {marmot_host}.

not rated 608 today A tokens not measured original MIT

add-datasource

132

grafana/gcx

Skill Claude CodeCodex ✓ vendor

Use for the implementation workflow that adds gcx CLI support for a datasource type not registered in internal/datasources/providers — query client, command constructors, DatasourceProvider registration. Trigger on "add support for an unsupported datasource type" or "new datasource type". NOT for creating or…

not rated 586 +9 today A 127 tokens original Apache-2.0

data_analysis

133

ArtificialAnalysis/Stirrup

Skill Claude CodeCodex

High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.

not rated 578 +4 11d ago A 44 tokens copy · 100% MIT

crawlseo AGENTS.md

134

crawlseo/crawlseo

Instructions file CodexOpenCode

AGENTS.md instructions for crawlseo/crawlseo, a project described as: Open-source SEO monitoring. GSC + Site Crawler + Core Web Vitals in one dashboard.

not rated 577 +9 today A 55 tokens original MIT

claude-dashboard

135

uppinote20/claude-dashboard

Plugin Claude Code

Bundles 4 commands, 1 hook · 52 tokens together

Unified status line for Claude Code with multi-CLI (Claude, Codex, Gemini, Antigravity, z.ai) usage monitoring, context, rate limits, and cost tracking.

not rated 565 +2 12d ago A tokens not measured original MIT

skvm-general

136

SJTU-IPADS/SkVM

Skill Claude CodeCodex

Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the user asks to "profile", "aot-compile", "bench", "run a single ad-hoc task with a skill", or asks about skvm proposals. Do NOT trigger for jit-optimize…

not rated 552 +1 7d ago C 107 tokens copy · 100% MIT

duckdb-skills

137

duckdb/duckdb-skills

Plugin Claude Code ✓ vendor

Bundles 9 skills · 597 tokens together

DuckDB-powered skills for Claude Code: read any data file, attach and query DuckDB databases, search DuckDB/DuckLake docs, search past session logs, and install/update DuckDB extensions.

not rated 538 +3 4mo ago A tokens not measured original MIT

clpeak AGENTS.md

138

krrishnarraj/clpeak

Instructions file CodexOpenCode

AGENTS.md instructions for krrishnarraj/clpeak, covering clpeak — "compute latency peak", architecture, directory map, build and quick lookups.

not rated 517 +2 today A 1,760 tokens original Apache-2.0

mcp-server-motherduck

139

motherduckdb/mcp-server-motherduck

MCP server Claude CodeCodexCursor +2

A MCP server for MotherDuck and local DuckDB. Runs locally from the mcp-server-motherduck Python package. Needs 8 environment variables to run.

not rated 517 +5 16d ago A tokens not measured original MIT

prometheus-mcp-server

140

pab1it0/prometheus-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server "prometheus-mcp-server" as configured in pab1it0/prometheus-mcp-server. Runs in Docker (ghcr.io/pab1it0/prometheus-mcp-server:1.6.2). Needs 14 environment variables to run.

not rated 514 +1 1mo ago A tokens not measured original MIT

consulting-analysis

141

MagicCube/agentara

Skill Claude CodeCodex

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…

not rated 504 +2 3mo ago A 110 tokens

wbh604/fund-guy-skill

Instructions file CodexOpenCode

A set of instructions for auditing a fund manager's investment decisions using public fund data. It produces an interactive HTML report and emphasizes separating managers' tenures and documenting missing information.

not rated 503 +52 changed yesterday A 702 tokens original MIT

just-fucking-cancel

143

rohunvora/just-fucking-cancel

Skill Claude CodeCodex

Analyze bank transaction CSVs to find recurring charges, categorize subscriptions, and cancel what you don't need. Use when user says "cancel subscriptions", "audit subscriptions", "find recurring charges", or "what am I paying for". Supports Apple Card, Chase, Mint, and generic CSV formats. Outputs interactive HTML…

not rated 498 +1 7mo ago A 75 tokens

ianlkl11234s/mini-taiwan-pulse

Skill Claude CodeCodex

A toolkit for measuring how easily places can be reached through a road network. It can show distances or travel areas around points of interest, such as shops, stations, or services.

not rated 495 +6 today A 239 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: