plan-tests

plan-tests is a cursor rule for Cursor from danielvm-git/bigpowers. It costs 35 tokens per session (728 once invoked), scanned A, original, MIT.

Design a risk-scaled test architecture for an epic before implementation begins. Produces prioritized scenarios, test level distribution, and fixture plans based on TEA and bigpowers principles.

Cursor rule for Cursor

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 rules/danielvm-git/bigpowers/plan-tests
Clone the repo
git clone --depth 1 https://github.com/danielvm-git/bigpowers

Made for: Cursor.

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.

agentmods badge for plan-tests

README.md
[![agentmods](https://agentmods.dev/badge/rules/danielvm-git/bigpowers/plan-tests.svg)](https://agentmods.dev/rules/danielvm-git/bigpowers/plan-tests)
Your own site
<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/plan-tests"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/plan-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00035 $0.00728
Opus 5 $0.00017 $0.00364
Sonnet 5 $0.00007 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured today against content hash c4ac2e69ffec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-tests 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 today.

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.

.cursor/rules/plan-tests.mdc · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Tests

Spine position: Between slice-tasks and plan-work for epics with risk: P0|P1. Optional (can be waived in state.yaml) for P2/P3.

Bridges the gap between slicing and planning by systematically designing the test suite as a first-class system. Produces specs/tech-architecture/eNN-TEST_PLAN_LATEST.md.

Pre-flight

  • Read specs/epics/eNN-*/ story list.

Core Workflow

  1. Analyze Epic: Read sliced stories in the active epic capsule.
  2. Risk Assessment: Map behaviors to P0–P3 risk tiers.
  3. Level Strategy: Classify each scenario (Unit, Integration, E2E).
  4. Fixture Design: Plan factories, network intercepts, mocks (see REFERENCE.md).
  5. NFR Plan: Define verifiable commands for Non-Functional Requirements. Skip if --lite.
  6. Publish: Generate specs/tech-architecture/eNN-TEST_PLAN_LATEST.md.

Hard Gates & Guardrails

  • DO NOT write test code or production code during this skill.
  • Scenario ID format MUST be: SC-eNNsYY-P{0|1|2|3}-NN.
  • plan-work MUST reference these scenario IDs in its §17 Gherkin acceptance criteria.
  • Default to pushing tests to the lowest possible level.

Execution Modes

  • $bmad plan-tests: Standard execution.
  • $bmad plan-tests --lite: Skips NFRs and complex fixture planning.

Verify

→ verify: test -f specs/tech-architecture/e32-TEST_PLAN_LATEST.md

Handoff

Gate: READY -> next: plan-work Writes: state.yaml handoff.next_skill = plan-work


Plan Tests — Reference

Test Plan Template (specs/tech-architecture/eNN-TEST_PLAN_LATEST.md)

# Test Design: [eNN-slug]

## 1. Risk Matrix & Scenarios
| Scenario ID | Behavior Description | Risk | Test Level | Target File/Module |
|-------------|----------------------|------|------------|--------------------|  
| SC-P0-01    | Primary checkout     | P0   | Integration | checkout.spec.ts  |

## 2. Fixture Architecture & Isolation
- Data Factories: (e.g. UserFactory)
- Network Intercepts: (e.g. MSW handlers)
- Database State: (e.g. in-memory SQLite)

## 3. NFR Verification
| NFR Type | Requirement | Verification Command |
|----------|-------------|----------------------|
| Perf     | < 200ms     | `npm run test:perf`  |

## 4. Out of Scope
- [Explicitly excluded testing areas]

Read the full file on GitHub · 75 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. today First seen · 75 lines · 35 tokens per session scan A c4ac2e69ffec

Subscribe to this mod's changes

plan-tests is a cursor rule published in the GitHub repository danielvm-git/bigpowers (163 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 728 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 2026-09-03.