A command that creates a focused test plan from recent code changes. It covers automated tests, manual checks, regressions, safeguards, and unanswered questions.

Use it after making changes to identify unit, integration, end-to-end, negative, and regression tests.

It turns a code diff into concrete checks, so important changed behavior is less likely to go untested.

test-plan — Command for coding agents by julianromli: A command that creates a focused test plan from…

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 commands/julianromli/droid-factory-template/test-plan

Clone the repo

git clone --depth 1 https://github.com/julianromli/droid-factory-template

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/julianromli/droid-factory-template/test-plan.svg)](https://agentmods.dev/commands/julianromli/droid-factory-template/test-plan)

Your own site

<a href="https://agentmods.dev/commands/julianromli/droid-factory-template/test-plan"><img src="https://agentmods.dev/badge/commands/julianromli/droid-factory-template/test-plan.svg" alt="Measured on agentmods" height="20"></a>

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 306 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.

Model	Per session	Once invoked
Fable 5	$0.00008	$0.00306
Opus 5	$0.00004	$0.00153
Sonnet 5	$0.00002	$0.00061
Haiku 4.5	$0.00001	$0.00031

Measured 5d ago against content hash 451d2318fc1d, 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 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 5d ago.

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.

commands/test-plan.md · 22 lines

What it actually says

You are a QA lead. Derive an actionable manual + automated test plan tailored to the latest code changes. Operate in READ-ONLY mode.

Workflow:

Invoke the Task tool with subagent_type: git-summarizer to capture repository context (diffs, file list, commits). Retain the Markdown output for downstream use.
If the git-summarizer output indicates no staged or unstaged changes, invoke the Task tool with subagent_type: test-coverage-reviewer first to gather broader coverage insights, then pass both summaries to the next step.
Call the Task tool with subagent_type: test-plan-writer, providing git-summarizer output, optional test-coverage-reviewer findings, $ARGUMENTS (treated as a feature/scope hint), and any relevant context. Request a concise yet thorough test matrix.
If the subagent fails, craft the plan manually using the collected data: map changed components to unit, integration, and end-to-end scenarios, include regression and negative cases, and reference required scripts or commands.

Respond with Markdown containing the following sections:

Summary
Automated Tests
Manual Scenarios
Regression / Guardrails
Open Questions

Each bullet should include pass criteria and any commands or data needed. Note - None when a section does not apply.

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.

5d ago First seen · 22 lines · 8 tokens per session scan A 451d2318fc1d

Subscribe to this mod's changes

test-plan is a command published in the GitHub repository julianromli/droid-factory-template (52 stars, last pushed 8mo ago), licensed MIT. It adds 8 tokens to every session and 306 once invoked, about $0.0000 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 2026-08-30.

Testing

test-plan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze