Agentry
Menu

blaktron/website-test-plan-runner

autonomousv0.1.0

Executes a supplied website test plan step by step and produces a detailed PDF report with results and evidence.

Declared capabilities

secrets: 2data: files, other

Capabilities are the author's declaration and the basis for policy and scanning. The registry cannot enforce them at run time. Your runtime should.

MCP servers & tools

agentry run serves exactly the tools this contract declares, through a per-run MCP gateway. An undeclared capability is a tool that does not exist at run time.

Tools the runner grants

Manifest declarationTool(s) granted
(always)write_report — reports → the run's output folder
(always)list_inputs, read_input, search_inputs — operator-provided input files, read-only
(always)scratch_list, scratch_read, scratch_write, scratch_search — the run's own scratch folder at /scratch, private to the run and deleted at its end; the runner's grant, not a line of the contract
(always)export_pdf — a Markdown report as a PDF in reports/, laid out in your report design; the runner's grant, not a line of the contract
(always)grep, glob — search file contents by regular expression and list files by path pattern (ripgrep), one area a call: the inputs, attached knowledge, /scratch; the runner's grant, not a line of the contract

MCP servers involved

  • QuickAgent Tools — the runner's companion server, served through a per-run Docker MCP Gateway; its tool surface is exactly the table above.
  • Operator-cataloged MCP servers may be attached for the declared dataAccess categories (files, other); undeclared categories are never wired in.

Keys & identities

SITE_USER, SITE_PASSWORD

The runner's guided setup collects these once into the QuickAgent's MCP profile, kept or removed per the operator's choice. Values are never published or shown.

In an embedded install

Installed into an existing coding agent (agentry install), the same contract maps to the host's built-in tools — enforcement there is the host's. Allowed tools: none declared (host defaults apply).

Install

agentry install blaktron/website-test-plan-runner@0.1.0
git clone https://secureagentry.net/blaktron/website-test-plan-runner.git
git clone ssh://git@git.secureagentry.net/blaktron/website-test-plan-runner.git

claude-skill is this agent's default target, so the flag is not needed.

agent.yaml

schemaVersion: "2"
name: website-test-plan-runner
namespace: blaktron
modes: [autonomous]
version: 0.1.0
summary: Executes a supplied website test plan step by step and produces a detailed PDF report with results and evidence.
license: MIT
tags: [website, testing, test-plan, pdf, quality-assurance]

entrypoints:
  instruction: AGENT.md

intake:
  - id: site
    prompt: The website to test (https://…)
    type: url
    required: true

inputs:
  kinds: [documents, data]
  view: text

guide:
  overview: Executes your detailed test plan against the website in a browser and returns a PDF report, its Markdown source and screenshot evidence. Reports each case and step with observed results, defects and reasons for anything it could not test. Supply the plan as attached files or knowledge.
  prepare: ["Provide a detailed plan with ordered steps, prerequisites, test data and expected results.", Use a staging environment and explicitly identify any permitted disposable-data or test-mode operations., "For existing-account tests, optionally provide SITE_USER and SITE_PASSWORD through the run's key setup.", Run on your own computer when the website is on your private network.]
  files: Attach the test plan as PDF, Word, Markdown, text or a spreadsheet, unless it is supplied through an attached knowledge pack.
  task: e.g. Execute release 2.4's regression plan on staging; disposable test records are permitted, but no messages or payments.
  connect:
    SITE_PASSWORD: Optional password for the dedicated test account named by SITE_USER. Store it through the run's key setup, not in the plan or task. Without both sign-in keys, cases requiring an existing account are reported as blocked.
    SITE_USER: Optional sign-in identifier for a dedicated test account on the website. Together with SITE_PASSWORD, enables existing-account cases. Use an account with only the permissions the plan requires; public cases run without it.

capabilities:
  network:
    egress: none
  filesystem:
    read: none
    write: none
  exec: none
  secrets: [SITE_USER, SITE_PASSWORD]
  dataAccess: [files, other]
  optionalSecrets: [SITE_USER, SITE_PASSWORD]

knowledge:
  accepts:
    prompt: Optionally attach your website test plan and supporting requirements as knowledge instead of, or alongside, plan files.

publish:
  include: [agent.yaml, AGENT.md, README.md, LICENSE]

Agentry uses only strictly necessary cookies — they sign you in and keep the site secure. Nothing here tracks you, and there are no advertising or analytics cookies. Privacy policy