claude-prospector
Claude Code efficiency and hygiene toolkit. Surfaces token spend across the three billing windows with per-model / per-agent / per-skill attribution, and audits your effective Claude Code configuration for agent and skill overlap.
Why
claude-prospector bundles a set of skills that target distinct angles of "is my Claude Code setup healthy?":
| Skill | Angle | |---|---| | usage-analysis | where your tokens are going | | usage-dashboard | regenerate the cost dashboard surface | | claude-audit | where your config has agent / skill overlap or bloat | | session-analysis | whether a session stayed on task (opt-in LLM judgment) |
Claude Code's built-in /usage shows current-session token totals and — for Max/Pro subscribers — plan-usage bars on the same screen. It doesn't surface multi-day history, per-agent attribution with sub-agent nesting, per-skill invocation counts, or per-project breakdowns, and there's no way to ask "where are my Sonnet-7d tokens going this week?" from inside the session. There's also no built-in way to detect when two installed plugins ship overlapping code-reviewer agents or near-duplicate skills.
claude-prospector reads Claude Code's local JSONL session files to break tokens down by model, agent (with sub-agent nesting), skill, and project across all three billing windows (5h rolling, 7d rolling, Sonnet-only 7d), and inventories your custom + plugin-provided agents and skills to produce a structured overlap / conflict report with keep / modify / drop recommendations.
Install
1. Add the marketplace and install the plugin
claude plugin marketplace add glitchwerks/plugins
claude plugin install claude-prospector@glitchwerks2. First-run setup
After installing (or after a plugin update), open a new Claude Code session. You will see a banner:
claude-prospector requires setup. Run /setup-prospector to materialise the Python venv. After setup completes, open a new session to activate the dashboard, skill-tracking, and usage-analysis features.
Run /setup-prospector once. The skill will:
- Discover a Python 3.10+ interpreter on your system.
- Create a plugin-owned venv at ${CLAUDEPLUGINDATA}/venv/.
- Install the plugin's exact claude-prospector version from PyPI into that venv.
- Verify the install and record a setup-state flag.
PyPI is always the preferred source. If that default exact-version install fails, /setup-prospector reports the failure and offers a source-build fallback; it does not use the fallback unless you explicitly approve it. The fallback resolves the matching v<plugin-version tag in the public repository to an immutable commit SHA, verifies the tag/SHA match, then downloads, builds, and installs that exact revision with the venv's Python and pip. This requires Git and GitHub access, and build/runtime dependencies must still be available from your configured package index or local cache. If CLAUDEPROSPECTORPIPSPEC is set, that override remains authoritative and a failed install does not trigger or offer the fallback.
After setup completes, open a new session — the banner will be gone and all features will work normally.
You will need to re-run /setup-prospector only when: