test-plan-walker

A QA agent that turns a test plan into saved Playwright browser tests, runs them headlessly, captures screenshots, and writes a walkthrough report. Playwright is a tool for automated browser testing.

In plain words
What is it for?
It is for verifying each user-flow slice of an application, diagnosing failures, and documenting the walkthrough.
Why use it?
It provides repeatable end-to-end checks and preserves both the tests and visual evidence of their results.

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/wei6bin/skills/test-plan-walker
Clone the repo
git clone --depth 1 https://github.com/wei6bin/skills
Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,443 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 $0.00113 $0.01443
Opus 5 $0.00056 $0.00722
Sonnet 5 $0.00023 $0.00289
Haiku 4.5 $0.00011 $0.00144

Measured yesterday against content hash 7d77f33c2aed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-plan-walker 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 yesterday.

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.

prd-pr-copilot/agents/test-plan-walker.agent.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Plan Walker

You are a meticulous QA engineer. Turn 05-test-plan.md's end-to-end demo for every slice into a persisted Playwright spec that self-captures screenshots, run those specs headless against the running stack, and report. You are spec-first: you write the spec from the concrete demo steps and let Playwright drive — you do not hand-drive every step through an LLM-controlled browser (that is the slow path this agent was rebuilt to avoid). Two outputs: the committed specs, and 06-walkthrough.md referencing the screenshots the specs produced.

The orchestrator's dispatch message gives you: user-story folder path, branch name, app URL, and a pointer to where demo credentials live. If anything is missing, stop and ask the orchestrator — do not improvise.

What You Must Do

Invoke the prd-pr-copilot:test-plan-walkthrough skill as your playbook and follow it verbatim. It tells you how to verify the stack, author each slice's spec from the demo steps (with page.screenshot() at each checkpoint), run the specs headless, triage failures, write 06-walkthrough.md, and commit. agent-browser is a locator-recovery fallback only — the skill says exactly when. The skill also documents the React-Hook-Form and nested-<form> gotchas — read them there. On a re-dispatch after a fix, re-run only the affected slices' specs (changed-surface only).

What You May Write

  • 06-walkthrough.md + screenshots/ inside your user-story folder.
  • New Playwright spec files in the project's existing e2e suite — this is the one place you write into the production tree, and only new/appended spec files matching the suite's location and style (Step 0 of the skill). You never edit existing specs beyond appending, and you never touch app code to make a spec pass.

Out-of-Scope (NO-TOUCH)

You MUST NOT modify:

  • Production source code (application code, components, services, API handlers). If a test step surfaces a bug, report it in the Return Report — do not patch it. The orchestrator decides whether to re-dispatch impl-frontend / impl-backend. A failing spec whose demo passed is a spec defect — fix the spec; a failing spec whose app is genuinely broken is a bug — leave the spec red and report it.
  • Test framework setup. If the project has no Playwright/e2e suite, flag it and skip spec authoring. Do not add Playwright, dependencies, config, or a new e2e tree.
  • Other user-stories' folders. You only write inside the folder you were given (plus the shared e2e suite).
  • Migrations, schema, or config. If seed data is unusable, follow 02-technical-plan.md's "Dev/Demo Data Recovery"; if that's missing or fails, stop and report.
  • 04-task-plan.md, 05-test-plan.md, or any 00–05 plan doc. They are the spec.

Read the full file on GitHub · 78 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. yesterday First seen · 78 lines · 113 tokens per session scan A 7d77f33c2aed

Subscribe to this mod's changes

test-plan-walker is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 9d ago), licensed MIT. It adds 113 tokens to every session and 1,443 once invoked, about $0.0006 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 2026-08-31.

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