tester Claude Code subagentA

tester from nexuslabs-ai/nxds is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add nexuslabs-ai/nxds/.claude/agents/tester.md@git:20261021.e743cb7

Pins git:20261021.e743cb7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
nexuslabs-ai/nxds
Path
.claude/agents/tester.md
Versions recorded
5
Latest version
git:20261021.e743cb7, committed Oct 21, 2026
First version recorded
Jan 19, 2026
Size
10,392 bytes
Repository stars
4
License
MIT

Testing specialist for test strategy, implementation, and quality assurance. Use proactively for implementing tests, designing test strategies, and ensuring test coverage.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Tester Agent

## Persona

Think like a **Senior QA Engineer / SDET** who believes that tests are the first line of defense against regressions.

## Mindset

- You've seen production bugs that could have been caught by a simple test
- You believe tests are documentation that actually runs
- You know that "given input → expect output" is the foundation of all good tests
- You value result validation over code coverage metrics
- You've debugged flaky tests at midnight and won't write another one

## Critical: No Shortcuts Policy

**NEVER use shortcuts to get things done.** When facing test failures or issues:

1. **Find the root cause** — Don't just make the test pass; understand WHY it's failing
2. **Propose proper solutions** — If fixing requires significant changes, discuss with user first
3. **Quality over speed** — We don't care about token usage or time. A proper fix is worth 10x the effort of a hack
4. **Ask when unsure** — If you're not confident about the right approach, ASK the user instead of guessing

| Shortcut ❌                        | Proper Approach ✅                      |
| ---------------------------------- | --------------------------------------- |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add nexuslabs-ai/nxds/.claude/agents/tester.md@sha256:f5e253f9ceb2219e

The line at the top of this page pins the label git:20261021.e743cb7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_t7yoyuvcgnx6thtu.svg)](https://markdownregistry.com/a/art_t7yoyuvcgnx6thtu)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in nexuslabs-ai/nxds/.claude/agents/tester.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of tester.md from somewhere else? Ask it: where did my tester.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Jan 19, 2026 and Oct 21, 2026, about one every 69 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261021.e743cb7 latest2026-10-21 e743cb7 10,392 BA view · diff
git:20260922.230cff52026-09-22 230cff5 10,395 BA view · diff
git:20260604.b326e5f2026-06-04 b326e5f 10,703 BA view · diff
git:20260519.75f34562026-05-19 75f3456 10,548 BA view · diff
git:20260119.219bf742026-01-19 219bf74 9,744 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (10392 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

nexuslabs-ai/nxds · 4 stars · license MIT · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_t7yoyuvcgnx6thtu
GET https://markdownregistry.com/api/v1/resolve?ref=nexuslabs-ai/nxds/.claude/agents/tester.md
GET https://markdownregistry.com/api/v1/blob/f5e253f9ceb2219eef316452d37b269fef4fdce551a06304741cdab872622232

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from nexuslabs-ai/nxds

analyze-deps-guide SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/analyze-deps-guide/SKILL.md · Analyze dependencies for updates, breaking changes, deprecations, and migration paths. Generates actionable reports…
git:20261021.e743cb7 · audit A · 4 stars
design-plan SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/design-plan/SKILL.md · Create implementation plans for complex tasks with architectural guidance. Use for complex features, multi-file…
git:20261021.e743cb7 · audit A · 4 stars
docs-writing SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/docs-writing/SKILL.md · Write or rewrite nxds docs prose in the plain nxds voice. Use when adding or editing a docs page…
git:20261021.e743cb7 · audit A · 4 stars
frontend-design SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/frontend-design/SKILL.md · Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to…
git:20260606.f17957a · audit A · 4 stars
implement-guide SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/implement-guide/SKILL.md · Draft a plan, stress-test it with a parallel review council, then implement in the main session. Only plan review is…
git:20260922.15c901b · audit A · 4 stars
implement-test-guide SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/implement-test-guide/SKILL.md · Implement tests with production-quality coverage. Use when implementing test suites, adding test coverage, or building…
git:20261023.046ec45 · audit A · 4 stars
modern-web-guidance SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/modern-web-guidance/SKILL.md · Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS…
git:20261021.e743cb7 · audit A · 4 stars
pr-fix-guide SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/pr-fix-guide/SKILL.md · Fix PR review issues directly without agent delegation. Combines root cause analysis and fixing into a single-agent…
git:20260606.f17957a · audit A · 4 stars
pr-review-follow-up SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/pr-review-follow-up/SKILL.md · Follow-up PR review to verify fixes after changes are pushed. Use when re-reviewing a PR after initial review feedback…
git:20261021.e743cb7 · audit A · 4 stars
pr-review-guide SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/pr-review-guide/SKILL.md · Review pull requests for code quality and architecture. Use when reviewing PRs, checking code changes, or evaluating…
git:20261021.e743cb7 · audit A · 4 stars
shadcn-adapt-guide SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/shadcn-adapt-guide/SKILL.md · Adapt a shadcn/ui component into a first-class nxds component. Use when porting, adapting, converting, or translating a…
git:20261029.b3d79a5 · audit A · 4 stars
shadcn SKILL.md skill
nexuslabs-ai/nxds · .agents/skills/shadcn/SKILL.md · Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides…
git:20260604.bbf12c8 · audit A · 4 stars

Every file in nexuslabs-ai/nxds

Other files named tester

tester SKILL.md skill
aiskillstore/marketplace · skills/0xsero/tester/SKILL.md · Updated skill
git:20260113.222b7de · audit B · 486 stars
tester Claude Code subagent
smith-horn/skillsmith · .claude/agents/core/tester.md · Comprehensive testing and quality assurance specialist
git:20260722.ed981fe · audit B · 78 stars
tester SKILL.md skill
crewrig/crewrig · .agents/skills/tester/SKILL.md · Test authoring and test-strategy skill. Activate when writing new tests, planning a test strategy, enumerating edge…
git:20261018.1588e62 · audit A · 24 stars
tester SKILL.md skill
crewrig/crewrig · .gemini/skills/tester/SKILL.md · Writes high-signal tests and plans test strategy: a regression test for a bug fix verified failing-then-passing, the…
git:20261113.93af61f · audit A · 24 stars
tester SKILL.md skill
crewrig/crewrig · .github/skills/tester/SKILL.md · Writes high-signal tests and plans test strategy: a regression test for a bug fix verified failing-then-passing, the…
git:20261113.93af61f · audit A · 24 stars
tester SKILL.md skill
crewrig/crewrig · .claude/skills/tester/SKILL.md · Writes high-signal tests and plans test strategy: a regression test for a bug fix verified failing-then-passing, the…
git:20261113.93af61f · audit A · 24 stars
tester SKILL.md skill
crewrig/crewrig · artifacts/core/skills/tester/SKILL.md · "Test authoring and test-strategy skill. Activate when writing
git:20261018.1588e62 · audit A · 24 stars
tester SKILL.md skill
peterzat/zat.env · claude/skills/tester/SKILL.md · Test strategy review and design from the perspective of a Principal SDE/T. `/tester` audits the current test strategy…
git:20261107.b47852a · audit A · 7 stars

Browse by kind, by grade A, or by owner.