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.

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.

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.

How tstockham96/claw-kit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tstockham96/claw-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tstockham96/claw-kit/main/.claude/agents/tester.md

Clone the repo

git clone --depth 1 https://github.com/tstockham96/claw-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/tstockham96/claw-kit/tester/github.svg)](https://agentmods.dev/agents/tstockham96/claw-kit/tester)

Your own site

<a href="https://agentmods.dev/agents/tstockham96/claw-kit/tester"><img src="https://agentmods.dev/badge/agents/tstockham96/claw-kit/tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/tstockham96/claw-kit/tester"><img src="https://agentmods.dev/badge/agents/tstockham96/claw-kit/tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01265
Opus 5.5	$0.00000	$0.00506
Sonnet 5.5	$0.00000	$0.00253
Haiku 4.5	$0.00000	$0.00127

Measured 2mo ago against content hash 05a491c68ec5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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

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

Phase 2: Setup Script

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

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
Check that the commands directory has all 5 slash commands
If setup.sh fails or produces errors, document exactly what went wrong
Write report to test-results/phase-2.md

Phase 3: Memory File Validation

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
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
Read example identity templates and verify they're complete
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.

2mo 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 8mo 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.

Claude Code E2E testing Testing ai-agent ai-memory anthropic claude openclaw

test

Verifies other agents' work on the running product: e2e, integration, unit and browser testing. Run once per handover, never per commit.

navid-kianfar/claude-memory-mcp · 34 tokens

gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

affaan-m/ECC · 32 tokens

e2e-runner

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

affaan-m/ECC · 69 tokens

claw-kit: Agent for Claude Code