Skill detail

agent-usage

Reports observed usage and quotas but does not optimize consumption.

MatchPossibleReviewed for less token usage

Sourcegg2gg/agent_eng_skillsExternal source

Reported installs1Popularity signal only

Inspect before use

Automated review checks relevance, not safety or endorsement. Read the source instructions before using this skill.

View on skills.sh (opens external page)Read SKILL.md on GitHub (opens external page)

Saved source preview

SKILL.md

The saved excerpt is a snapshot from review. The external source remains the complete and most current version.

---
name: agent-usage
description: >
  Show accurate Claude/Codex account usage from provider quota APIs where exposed and local session ledgers otherwise.
triggers:
  - /usage
  - agent usage
  - claude usage
  - codex usage
  - quota
allowed-tools:
  - Bash
---

# Agent Usage

Use when the user asks for current Claude, Claude Max, Claude Pro, Codex, or
agent account usage.

Run the local monitor from the Agent Engineering repo:

```bash
AGENTIC_ENGINEERING_HOME="${AGENTIC_ENGINEERING_HOME:-$HOME/Sync/agentic/gitlab-repos/org-internal/agentic-engineering}"
"$AGENTIC_ENGINEERING_HOME/stack/telemetry/agent-usage-monitor.py" --refresh
```

For a browser view:

```bash
AGENTIC_ENGINEERING_HOME="${AGENTIC_ENGINEERING_HOME:-$HOME/Sync/agentic/gitlab-repos/org-internal/agentic-engineering}"
"$AGENTIC_ENGINEERING_HOME/stack/telemetry/agent-usage-monitor.py" --html /tmp/agent-usage.html --watch 60
```

Do not estimate missing quota. If Codex plan quota is unavailable through the
Codex CLI, report the local observed token ledger and say provider quota is not
exposed.

Read the full source on GitHub

Context