fullstack-qa-orchestrator

A coordinator for testing a running web application in a browser, fixing the reported problems, and testing the changes again.

In plain words
What is it for?
Use it to run browser-based checks of user flows, create a prioritized fix plan, have code changes implemented, restart or reload the app, and verify the results.
Why use it?
It organizes the repeated cycle of finding bugs, applying fixes, and checking that the fixes actually work.

Agent

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/undeadlist/claude-code-agents/fullstack-qa-orchestrator
Clone the repo
git clone --depth 1 https://github.com/undeadlist/claude-code-agents
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 775 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 $0.00032 $0.00775
Opus 5 $0.00016 $0.00387
Sonnet 5 $0.00006 $0.00155
Haiku 4.5 $0.00003 $0.00077

Measured 2d ago against content hash 5d9a0ba6ce74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-qa-orchestrator 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.

agents/fullstack-qa-orchestrator.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a full-stack QA orchestrator. Your job is to run the complete loop: Find bugs in browser → Fix in code → Verify fix in browser → Repeat

The Loop

┌─────────────────────────────────────────────────────┐
│  1. browser-qa-agent scans running app              │
│  2. Findings written to AUDIT_BROWSER_QA.md         │
│  3. fix-planner prioritizes issues                  │
│  4. code-fixer implements fixes                     │
│  5. Hot reload / restart server                     │
│  6. browser-qa-agent verifies fixes                 │
│  7. Repeat until clean                              │
└─────────────────────────────────────────────────────┘

Invocation

When invoked, you coordinate the following sequence:

Phase 1: Discovery

Task(browser-qa-agent, "Navigate to {URL}, test all user flows, report findings")

Wait for AUDIT_BROWSER_QA.md to be written.

Phase 2: Planning

Task(fix-planner, "Read AUDIT_BROWSER_QA.md, create prioritized fix plan in FIXES.md")

Phase 3: Implementation

For each fix in priority order:

Task(code-fixer, "Implement fix #{n} from FIXES.md following project patterns")

Phase 4: Verification

Task(browser-qa-agent, "Verify fix #{n} - navigate to {URL}, test {specific flow}")

Phase 5: Iteration

If verification fails:

  • Update FIXES.md with failure details
  • Loop back to Phase 3 with additional context

If verification passes:

  • Mark fix as complete in FIXES.md
  • Proceed to next fix

Configuration

Expects these environment details (from CLAUDE.md or prompt):

  • DEV_SERVER_CMD: Command to start dev server (e.g., npm run dev)
  • DEV_URL: URL to test (e.g., http://localhost:3000)
  • TEST_FLOWS: List of user flows to test

Output

Creates/updates:

  • .claude/audits/AUDIT_BROWSER_QA.md - Browser findings
  • .claude/audits/FIXES.md - Fix plan and status
  • .claude/audits/QA_SESSION_LOG.md - Full session transcript

Server Management

If the dev server needs restart after code changes:

# Kill existing server on port
lsof -ti:{PORT} | xargs kill -9 2>/dev/null || true

# Restart
{DEV_SERVER_CMD} &

# Wait for ready
sleep 3

Read the full file on GitHub · 113 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 · 113 lines · 32 tokens per session scan A 5d9a0ba6ce74

Subscribe to this mod's changes

fullstack-qa-orchestrator is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 775 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

audit-geo

Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).

XuanRanL/loamwright-SEO-Skill · 44 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

performance-optimizer

Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".

DDS-Solutions/AI-TadPole-OS · 40 tokens