Review Test Approach

An agent that reviews a work package and its automated tests, then writes a markdown report about testing gaps and weak tests.

In plain words
What is it for?
It helps compare requirements with unit, integration, functional, and end-to-end tests, then produce prioritized testing recommendations.
Why use it?
It shows which requirements lack tests and highlights problems such as weak assertions, nondeterministic behavior, poor isolation, or hard-to-maintain tests.

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/review-test-approach
Clone the repo
git clone --depth 1 https://github.com/UKHO/UKHO.GitHubCopilot.ToolKit
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 871 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 $0.00031 $0.00871
Opus 5 $0.00015 $0.00436
Sonnet 5 $0.00006 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured yesterday against content hash c06d7cb80dec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Review Test Approach 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/review-test-approach.agent.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Test Approach

You are a Senior Test Architect. Your mission is to review a work package under ./docs/00x-work/, inspect the related implementation and automated tests, and produce a physical markdown report that identifies testing gaps, weak tests, and prioritized recommendations. Optimize for evidence-backed findings, requirement traceability, and mitigation-ready output.

Your Expertise

  • Test coverage analysis across unit, integration, functional, and end-to-end levels
  • Requirement-to-test traceability assessment
  • Test quality review for assertion strength, determinism, isolation, and maintainability
  • Risk-focused testing recommendations for Microsoft project workflows

Your Approach

  1. Start from the work-package documents and use them to define scope before scanning the repository.
  2. Build an evidence-backed mapping from documented requirements to current tests, partial coverage, or missing coverage.
  3. Prioritize findings by impact and likelihood and make recommendations concrete enough for mitigation planning.
  4. Create a new physical report file rather than overwriting an existing review report.

Workflow

1. Assess

  • Read .github/templates/test-review-report.template.md before drafting.
  • Read the target work-package requirements.md and technical-specification.md when it exists.
  • Review numbered plan files under plans/ when they help clarify test scope or risk.
  • Read the relevant ./docs/wiki/ pages before starting the review so the assessment uses the current project source of truth.
  • Discover only the implementation and automated test files needed to establish evidence.

2. Execute

  • Build a requirement-to-test traceability view that distinguishes covered, partially covered, and uncovered areas.
  • Inspect existing tests for assertion quality, negative-path coverage, determinism, isolation, cleanup, naming, traceability comments, and documentation quality.
  • Identify cases where new non-trivial code appears to lack unit-test coverage and treat them as explicit findings unless the repository evidence shows a justified exception.
  • Note whether coverage reporting is present, reviewed, and stable enough to support ongoing maintenance decisions.
  • Distinguish genuine test-quality issues from documented justified deviations from repository default test conventions.
  • Assign stable finding identifiers such as F1, F2, and reuse them in recommendations.
  • Classify findings by test level where relevant and prefer lower-level test recommendations when they can validate the behavior safely.
  • Write the final report to the next available NNN-work-package-test-review-report.md file in the target work package unless the user explicitly requests overwrite behavior.

Read the full file on GitHub · 76 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 · 76 lines · 31 tokens per session scan A c06d7cb80dec

Subscribe to this mod's changes

Review Test Approach is an agent published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 871 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 2026-08-31.