Live-agent chaos testing — spawn diverse persona agents against the running dev server, each with playwright browser tools and a distinct exploration mandate. Use when the user says "chaos test", "stress test the UI", "find bugs by exploring", "monkey test the site", or invokes `/chaos-test`. Personas are non-deterministic explorers, NOT chromedp scripts — they make judgment calls, follow surprising paths, and report what they tried. Triggers on phrases like "chaos monkey", "exploratory testing", "stress the UI", "agentic testing".
Installation
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Live-agent chaos testing — spawn diverse persona agents against the running dev server, each with playwright browser tools and a distinct exploration mandate. Use when the user says "chaos test", "stress test the UI", "find bugs by exploring", "monkey test the site", or invokes `/chaos-test`. Personas are non-deterministic explorers, NOT chromedp scripts — they make judgment calls, follow surprising paths, and report what they tried. Triggers on phrases like "chaos monkey", "exploratory testing", "stress the UI", "agentic testing".
Chaos-test — live exploratory testing via diverse persona agents
When this skill is invoked, you are the orchestrator. The skill replaces
deterministic chromedp tests with live agents who actually drive a browser
and make judgment calls.
When to use
Invoke this skill when:
The user wants stress / chaos / exploratory testing of a running UI
You've shipped a UI change and want to surface what a curious user finds
Do NOT use this skill for:
Adding regression tests (use chromedp in examples/site/e2e_*.go)
Code review (use Agent with general-purpose or ui-ux-advisor)
Static analysis of the codebase
Pre-flight
Before spawning personas, confirm:
The dev server is running at the target URL (default http://localhost:8082).
Check with curl -s -o /dev/null -w "%{http_code}\n" <url>. If not 2xx, ask
the user to run ./scripts/dev-watch.sh (or override target via args).
A run directory exists. Create /tmp/gofastr-chaos/<ISO-timestamp>/.
Each persona writes a <persona>.md report there.
Personas (7)
Spawn in parallel via Agent tool with subagent_type=chaos-<persona-name>:
Persona
Mandate
chaos-rage-clicker
Spam clicks, double-clicks, drags. Surface race conditions and stuck UI states.
Throttle network/CPU, drop requests, go offline. Check graceful degradation.
chaos-screen-reader
Use accessibility tree. Validate aria-live announcements, landmarks, focus announcements.
Each agent has playwright browser tools and writes its findings to
/tmp/gofastr-chaos/<run>/<persona>.md in the structured format defined
in its own agent file.
Spawning protocol
Confirm dev server is reachable.
Make the run directory.
Spawn all 7 personas in parallel via a single message with 7 Agent
tool-use blocks. The dev server handles the concurrency. Each agent gets:
The target URL
The path to its report file
A 10-minute time budget (the agent decides when to stop)
Wait for all 7 to return.
Read every report file. Collate into a single triage doc at
/tmp/gofastr-chaos/<run>/summary.md with sections:
Critical findings — bugs that crash, lose data, fail WCAG-A, or render
content unreadable. Cite which persona found each + reproduction steps.
What worked — paths every persona reported as smooth (lets you see
where the code is genuinely solid, not just where bugs are).
Inter-persona corroboration — findings reported by ≥2 personas get
promoted (high-signal, multi-angle confirmation).
Present the summary to the user with a recommendation: fix all,
triage tier-1 only, or accept as-is. The user picks.
Pi delegation
If you have mcp__pi__* available and the orchestration phase needs:
Cross-report deduplication (5 personas all flagged a contrast issue)
Severity classification of a long list
Summarization of repetitive findings
…delegate via mcp__pi__pi_delegate or mcp__pi__pi_swarm. The
browser-driving work stays with Claude Agents (playwright is a Claude MCP).
Cost note
Seven parallel playwright sessions for ~5–10 min each = serious token spend.
Tell the user up front: "Round 7 of chaos-test fires 7 agents in parallel —
this'll take ~10 min and burn tokens. Proceed?" Default to yes if the user
already invoked the skill.
Args
--target <url> — override the default http://localhost:8082
--persona <name> — run just one persona instead of all seven
--budget <min> — per-agent time budget in minutes (default 10)
What success looks like
A summary.md that:
Is short enough to read in 5 minutes (cap each tier at 7 items)
Names specific reproduction steps for every critical finding
Cites which persona surfaced each issue (so you can ask follow-ups)
Distinguishes "X is broken" from "X is a UX rough edge"
Names the things that worked, not just the bugs
Then leave the run directory in place — it's a paper trail.
