KPIs — Development skill for Claude Code
Ingest any new harness sessions and recompute the six Maxwell KPIs, then summarise the latest datapoints.
How to install KPIs
Installs to ~/.claude/commands/onfinance-maxwell-kpis.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/OnFinance/Maxwell/HEAD/.claude/commands/kpis.md -o ~/.claude/commands/onfinance-maxwell-kpis.md Restart Claude Code, or start a new session, for it to be picked up.
What KPIs does
description: Ingest any new harness sessions and recompute the six Maxwell KPIs, then summarise the latest datapoints allowed-tools: Bash(npm run *), Bash(node .claude/scripts/*), Read x-maxwell: workflow: kpis touches: ["kpis/data/**", "kpis/measurement/runs.jsonl"] readsCredentials: false
Run `npm run kpis -- $ARGUMENTS` (arguments may be `--company
Alternatives in Development
- Portaljs Add Geo — Auto-ingest a geospatial file (GeoJSON, Shapefile, GeoPackage, KML/KMZ, FlatGeobuf, CSV-with-geometry) into a 2.3k ★
- Magnitude — Open source inference server your agent sets up for you 1.5k ★
- Brain — Set up or use your Professional Brain — init, ingest, recall, or review 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ctxprof
Profile Claude Code JSONL sessions into six estimated token buckets, compare runs, and identify large context
Paper Trail Ingest All
Batch INGEST across the entire vault. Scans all SOTAs, identifies those with bibliographic sections containing
Load Handoff
If the user invokes as 'load-handoff latest' then just load the most recent HANDOFF file in the project's hand
Kshana Run
Run a validated Kshana PNT scenario via the kshana-mcp server and summarise the figures of merit
Deps Macros Ergonomics
Rust Intel — Dependencies, Macros & Ergonomics (supply-chain, clone, proc-macro, features, workspace, Deref, r
Loop Maker
Interviews you, then scaffolds a self-running agent loop. Cross-harness (Claude Code / Codex / Hermes / OpenCl
Related Agents
Decision Scout
Scans a repository and its Claude Code session logs, then returns a compact "decision dossier" — the raw mater
Scope Controls
Controls orchestrator — dispatches six subagents in two waves (org-wide issues, detections, dashboard ideas, p
Stagehand Expert
Use this agent when you need executable Stagehand test files for TDD workflow. ALWAYS checks latest Stagehand