test-plan-generator

A test-planning skill that turns product requirements, architecture documents, pull requests, and risky changes into an ordered list of tests. TDD, or test-driven development, is a practice of writing tests before implementation; this skill plans tests whether or not that practice is used.

In plain words
What is it for?
Use it to plan unit, integration, end-to-end, regression, and edge-case tests for new features, bug fixes, releases, and other changes.
Why use it?
It reduces missed coverage by tracing requirements, interfaces, security rules, errors, edge cases, performance, and accessibility needs to specific tests.

Skill for Claude CodeCodex

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 skills/firstp1ck/pi-coding-agent-forge/test-plan-generator
Any agent
npx skills add Firstp1ck/pi-coding-agent-forge --skill test-plan-generator
Clone the repo
git clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forge

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 733 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 $0.00051 $0.00733
Opus 5 $0.00026 $0.00367
Sonnet 5 $0.00010 $0.00147
Haiku 4.5 $0.00005 $0.00073

Measured 3d ago against content hash 98b02ba205ca, 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-generator 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 3d 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.

pi-skill-test-plan-generator/skills/test-plan-generator/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Plan Generator

Generate structured, prioritized test plans from spec and architecture documents.

Inputs

  • projects/<project-name>/combined-plan.md (primary source of truth)
  • projects/<project-name>/spec.md (original requirements)
  • projects/<project-name>/architecture.md (module boundaries and interfaces)
  • Forge's completion report (existing test coverage)

Process

Step 1 — Extract Requirements

Read the combined plan and extract every testable requirement:

  • Explicit acceptance criteria from the spec
  • Interface contracts from the architecture
  • Security constraints from Zero's review
  • Error handling expectations
  • Edge cases mentioned in the spec
  • Non-functional requirements (performance, accessibility)

Step 2 — Derive Test Cases

For each requirement, create one or more test cases:

| ID | Requirement | Test Case | Category | Priority | Status |
|---|---|---|---|---|---|
| TC-001 | User can create account | Valid email + password creates account | E2E | P0 | Pending |
| TC-002 | User can create account | Duplicate email rejected with error | E2E | P0 | Pending |
| TC-003 | Email validation | Invalid format "foo@" rejected | Unit | P1 | Pending |
| TC-004 | Rate limit on login | 6th attempt within 1 min returns 429 | Integration | P1 | Pending |

Step 3 — Prioritize

Use this priority scheme:

Priority Criteria Examples
P0 (Must test) Core user flows, data integrity, auth Login, create, read, update, delete
P1 (Should test) Error handling, edge cases, security functional Invalid input, rate limits, empty states
P2 (Nice to test) Boundary values, concurrent access, rare paths Max-length input, simultaneous edits
P3 (If time allows) Cosmetic, UX polish, accessibility Layout consistency, keyboard navigation

Step 4 — Coverage Analysis

Compare test cases against spec requirements:

## Coverage Matrix

| Spec Section | Requirements | Test Cases | Coverage |
|---|---|---|---|
| Authentication | 5 | 12 | 100% |
| User Profile | 3 | 6 | 100% |
| Data Export | 2 | 1 | 50% — missing error path tests |

Read the full file on GitHub · 104 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. 3d ago First seen · 104 lines · 51 tokens per session scan A 98b02ba205ca

Subscribe to this mod's changes

test-plan-generator is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (74 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 733 once invoked, about $0.0003 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.

Related

Other skills, from other repositories