Token Meter Tester — Development agent for Claude Code
Independently verify one Token Meter head and report evidence without fixing it.
How to install Token Meter Tester
Installs to ~/.claude/agents/splunk-token-meter-token-meter-tester.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/splunk/token-meter/HEAD/.claude/agents/token-meter-tester.md -o ~/.claude/agents/splunk-token-meter-token-meter-tester.md Restart Claude Code, or start a new session, for it to be picked up.
What Token Meter Tester does
name: token-meter-tester description: Independently verify one Token Meter head and report evidence without fixing it. tools: Read, Grep, Glob, Bash disallowedTools: Agent skills:
- token-meter-verification
Before acting, read `.agents/roles/tester.md` completely. Read the task envelope and its referenced workflow contracts. Follow the canonical role and preloaded project skill as bin
Alternatives in Development
- Get Commit ID — gh api repos/OWNER/REPO/pulls/PR_NUMBER --jq '.head.sha' gh api repos/OWNER/REPO/pulls/PR_NUMBER/comments \ 1.3k ★
- CSRF Hunter — CSRF specialist (H1 #57) 812 ★
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Token Meter Reviewer
Independently review one Token Meter base-to-head change and return findings first.
Gui Tester
Run GUI tests and report results. Use after GUI changes to verify nothing is broken.
Verification Challenger
Independently challenge an implementation by tracing requirements to tests and evidence, checking regressions
Token Meter Communication Manager
Draft and quality-check all Token Meter contributor- and user-facing communication.
Corp Comms
Head of Corporate Communications — external communications; cannot release without GC clearance. Use for press
Backend Reviewer
Use to independently review backend code changes against the backend review checklist and open a draft PR once
Related Skills
Execute Test Cases
Thực thi manual test cases trên browser thật qua Playwright MCP — chấm PASS/FAIL/BLOCKED/SKIPPED, thu evidence
Verify Install
Check a Backbrief Kit install and report a plain pass/fail list. Reads only; never changes anything without a
Docforge
Writes new repository documentation from source-code evidence — catalog-driven, provenance-tracked, and indepe