hummbl-io/agent-skills/agent-usage-report

Claude Code and agent skill by hummbl-io/agent-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Report named-agent usage telemetry, citation counts, first/last use, and backfill coverage for Apex/ARCANA-style agent promotion decisions. Use when asked about agent usage, lens telemetry, who is getting cited, citation counts, or named-agent promotion evidence.

Install

npx vskill@latest install hummbl-io/agent-skills/agent-usage-report

SKILL.md

The same SKILL.md was published earlier as hummbl-io/agent-skills/agent-usage-report.

Agent Usage Report

Render the named-agent usage histogram from:

$env:USERPROFILE\_internal\telemetry\agent-usage.jsonl

Default command:

powershell
python $env:USERPROFILE\bin\agent-usage-report.py

Useful variants:

powershell
python $env:USERPROFILE\bin\agent-usage-report.py --all
python $env:USERPROFILE\bin\agent-usage-report.py --agent apex
python $env:USERPROFILE\bin\agent-usage-report.py --cluster arcana
python $env:USERPROFILE\bin\agent-usage-report.py --days 30

If telemetry is missing or empty, run a dry-run backfill first:

powershell
python $env:USERPROFILE\bin\agent-usage-backfill.py --dry-run

Backfill scans Claude session JSONL Agent tool-use records. It does not persist or report prompt bodies. Free-text AAR and bus messages are intentionally not mined as promotion evidence.

Then, if the dry-run output is plausible, write backfilled records:

powershell
python $env:USERPROFILE\bin\agent-usage-backfill.py

Report the histogram sorted by ascending citation count. For promotion or retirement recommendations, cite:

  • telemetry path
  • report window
  • citation count
  • first and last use
  • whether records are live or backfilled

Do not treat backfilled records as full runtime instrumentation. They are a Phase 0 proxy until Agent-tool auto-logging exists.

Cloudflare Neuron Usage

For Cloudflare Workers AI Neuron consumption tracking, use the usage-monitor tool:

bash
python ~/bin/usage_monitor.py status # today's Neuron usage
python ~/bin/usage_monitor.py trend # 7-day trend
python ~/bin/usage_monitor.py export --format csv # export for reporting

See [usage-monitor] skill for details.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/hummbl-io/agent-skills/agent-usage-report/badge)](https://verified-skill.com/skills/hummbl-io/agent-skills/agent-usage-report)

Something wrong with this skill or its page? Tell us.