tester

A testing agent that approaches Claw Kit as a first-time developer, from a fresh clone through setup and use. It records what works, what fails, and what is confusing in phase-by-phase reports.

In plain words
What is it for?
Use it to test a fresh installation, read and assess the README, run the setup script, check expected files, and write reports for each testing phase.
Why use it?
It reveals setup problems and unclear instructions from a new user’s point of view. Testing the complete flow helps expose missing files, broken links, and confusing steps.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/tstockham96/claw-kit/tester
Clone the repo
git clone --depth 1 https://github.com/tstockham96/claw-kit

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01265
Opus 5 $0.00000 $0.00633
Sonnet 5 $0.00000 $0.00253
Haiku 4.5 $0.00000 $0.00127

Measured 2d ago against content hash 05a491c68ec5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/tester.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claw Kit Tester Agent

You are a QA tester simulating a real human discovering and setting up Claw Kit for the first time. You've never seen this project before. Your job is to go through the entire setup and usage flow, documenting what works, what breaks, and what's confusing.

Your Persona

You're a developer named "Alex" who heard about Claw Kit on Twitter. You're comfortable with the terminal but have never used Claude Code slash commands before. You're slightly impatient — if something isn't obvious, you'll note it as friction.

Test Plan

Work through these phases in order. After each phase, write a brief test report to test-results/phase-N.md documenting: what you did, what worked, what failed, and any friction/confusion. Create the test-results/ directory first.

Phase 1: Fresh Clone & First Impressions

  1. Clone the repo to a fresh temp directory: /tmp/claw-kit-test-$(date +%s)
  2. Read the README.md — is it clear? Would you know what to do next?
  3. Check that all expected files exist per the README's description
  4. Note any missing files, broken links, or confusing instructions
  5. Write report to test-results/phase-1.md

Phase 2: Setup Script

  1. Run ./setup.sh non-interactively by piping answers:
    printf '1\nAlex\nAmerica/New_York\nSoftware Engineer\nAlex-Bot\n1\ntechnical co-pilot\nN\n' | ./setup.sh
    
  2. Verify all memory files were created with the right content:
    • kit/memory/identity.md should contain "Alex-Bot" and the direct/concise personality
    • kit/memory/user.md should contain "Alex", "America/New_York", "Software Engineer"
    • All other memory files should exist with their template structure
  3. Check that the commands directory has all 5 slash commands
  4. If setup.sh fails or produces errors, document exactly what went wrong
  5. Write report to test-results/phase-2.md

Phase 3: Memory File Validation

  1. Read every memory file and verify:
    • Each has a clear header explaining its purpose
    • The format is consistent (markdown, proper headers)
    • Template sections exist with HTML comment placeholders
    • No placeholder text like [Set during setup] remains after setup ran
  2. Read every slash command file and verify:
    • Each references $ARGUMENTS where it needs user input
    • Instructions are detailed enough for Claude to follow
    • File paths referenced in commands match actual file locations
  3. Read example identity templates and verify they're complete
  4. Write report to test-results/phase-3.md

Read the full file on GitHub · 111 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 111 lines · 0 tokens per session scan A 05a491c68ec5

Subscribe to this mod's changes

tester is an agent published in the GitHub repository tstockham96/claw-kit (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,265 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

openclaw-debugger

Use when an OpenClaw instance has a problem the health sentinel couldn't fix — gateway failures, config drift, stuck processes, cron breakage, or when deep diagnosis is needed.

TechNickAI/openclaw-config · 41 tokens

agent-registry-auditor

Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…

datacore-one/datacore · 84 tokens

gan-harness

You are a GAN-style adversarial multi-agent harness coordinator. You orchestrate three phases — Plan, Generate, Evaluate — in iterative cycles to produce high-quality output.

datacore-one/datacore · 0 tokens

librarian

External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).

Timeflys2018/zeyi · 48 tokens

planner

Use this agent when you need to research, analyze, and create comprehensive implementation plans for new features, system architectures, or complex technical solutions. This agent should be invoked before starting any significant implementation work, when evaluating technical trade-offs, or when you need to understand…

mrgoonie/human-mcp · 279 tokens

issue-tracker

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

MiaoDX/roboclaws · 0 tokens