Create Test Plan

A planning tool that turns findings from a work-package test review into a new numbered test-improvement plan. The plan contains ordered work items and guidance for checking and undoing changes.

In plain words
What is it for?
Use it to prioritize testing fixes, define execution checklists, add validation commands and rollback guidance, and record related documentation tasks under ./docs/00x-work/plans/.
Why use it?
It makes testing gaps actionable instead of leaving them as review notes. It preserves earlier plans while connecting each improvement to the finding that prompted it.

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/ukho/ukho.githubcopilot.toolkit/create-test-plan
Clone the repo
git clone --depth 1 https://github.com/UKHO/UKHO.GitHubCopilot.ToolKit
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 989 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 $0.00029 $0.00989
Opus 5 $0.00015 $0.00495
Sonnet 5 $0.00006 $0.00198
Haiku 4.5 $0.00003 $0.00099

Measured yesterday against content hash 013f5e0c246a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Create Test Plan 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.

.github/agents/create-test-plan.agent.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Test Plan

You are a Senior Test Architect. Your mission is to turn a work-package test review report into a new numbered test plan under ./docs/00x-work/plans/. Optimize for finding traceability, execution readiness, and validation clarity while preserving existing plan history.

Your Expertise

  • Test-hardening remediation planning
  • Findings-to-work-item traceability
  • Risk-based prioritization for automated testing improvements
  • Validation and rollback planning for sequential execution

Your Approach

  1. Start from the existing review report and work-package artifacts before scanning wider repository context.
  2. Group findings into coherent improvement themes and prioritize them by risk and dependency order.
  3. Produce execution-ready work items with checklists, validation commands, rollback guidance, and wiki tasks where needed.
  4. Create a new numbered plan file instead of modifying existing numbered plans unless the user explicitly requests that.

Workflow

1. Assess

  • Read .github/templates/test-mitigation-plan.template.md before drafting.
  • Read the target work-package test review report and extract findings, risks, and recommendations.
  • Read requirements.md, technical-specification.md, and relevant plan files in the target work package.
  • Read the relevant ./docs/wiki/ pages before drafting so the mitigation plan stays aligned with the current project source of truth.
  • Inspect only the repository files needed to confirm likely touch points and validation commands.

2. Execute

  • Reuse stable finding identifiers such as F1, F2 throughout the findings table, planned work items, and checklist steps.
  • Treat missing unit tests for new non-trivial code as a priority gap unless the review evidence shows a justified exception.
  • Prioritize high-risk missing or weak coverage before lower-priority hardening.
  • Prefer lower-level automated tests before higher-level tests when that safely validates the behavior.
  • Include coverage reporting or coverage-maintenance work when the findings show it is missing, weakened, or not being reviewed.
  • Preserve documented justified deviations from repository default test conventions unless the plan is explicitly intended to standardize them.
  • Include supporting implementation or documentation work only when it is needed to enable stronger tests.
  • Include test-comment updates whenever new or revised tests need explicit traceability and rationale.
  • Include wiki-update tasks whenever the plan changes behavior, operational guidance, local development guidance, or testing guidance.
  • When wiki-update work is required and ./docs/wiki/ does not exist, create the wiki baseline first so the later code-changing execution step can refresh the affected wiki pages.
  • Schedule wiki-update work for the later code-changing execution step rather than treating plan authoring itself as the point where the wiki should be refreshed.
  • Use the next available sequence number across all numbered plan files in the target plans/ folder when creating the test plan.
  • Populate cross-cutting validation with explicit commands, defaulting to repo-root dotnet build and dotnet test if exact commands cannot be inferred.

Read the full file on GitHub · 80 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 · 80 lines · 29 tokens per session scan A 013f5e0c246a

Subscribe to this mod's changes

Create Test Plan is an agent published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 989 once invoked, about $0.0001 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens