ratary: Skill for Cursor

.cursor/skills/forge-prove/SKILL.md

forge-prove is a skill for Cursor from ontorata/ratary. It costs 26 tokens per session (261 once invoked), scanned A, original, MIT.

A testing procedure for code changes that follows a failing test, a minimal fix, and a passing test suite. This is an evidence-first version of test-driven development, or TDD, where tests guide the implementation.

In plain words
What is it for?
Use it during behavior changes to write focused tests, confirm the intended failure, implement the smallest fix, run the relevant tests, and refactor only after they pass.
Why use it?
It provides proof that a behavior change works and discourages code written before its expected behavior is tested. It also prevents bypassing failures by weakening or deleting tests.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is ontorata/ratary's own configuration. It tells Cursor how to work on ratary itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ratary configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ontorata/ratary. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ontorata/ratary/main/.cursor/skills/forge-prove/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ontorata/ratary

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 forge-prove

README.md
[![agentmods](https://agentmods.dev/badge/skills/ontorata/ratary/forge-prove.svg)](https://agentmods.dev/skills/ontorata/ratary/forge-prove)
Your own site
<a href="https://agentmods.dev/skills/ontorata/ratary/forge-prove"><img src="https://agentmods.dev/badge/skills/ontorata/ratary/forge-prove.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00026 $0.00261
Opus 5 $0.00013 $0.00130
Sonnet 5 $0.00005 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 7d ago against content hash 116f87001274, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

forge-prove 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 7d 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.

.cursor/skills/forge-prove/SKILL.md · 40 lines

What it actually says

Forge Prove

Activates: during forge-execute when behavior changes.

Cycle

  1. Red — write or extend a test that fails for the right reason
  2. Witness — run test; confirm failure message matches intent
  3. Green — minimal production code to pass
  4. Witness — full relevant suite passes
  5. Refactor — only with green tests; no scope expansion

Anti-patterns (reject)

  • Production code before any failing test (unless pure refactor with full coverage)
  • Tests that always pass regardless of implementation
  • Deleting tests to go green
  • skip / @ts-ignore to bypass without owner OK

Commands

npm test -- path/to/focused.test.ts
npm test   # before task complete

Prompt cross-ref

docs-ai/cross-cutting/agent-forge/workflow/prompts/testing/unit-test-design.md

When to skip

Docs-only or comment-only — run lint/typecheck instead.

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. 7d ago First seen · 40 lines · 26 tokens per session scan A 116f87001274

Subscribe to this mod's changes

forge-prove is a skill published in the GitHub repository ontorata/ratary (1 stars, last pushed 28d ago), licensed MIT. It adds 26 tokens to every session and 261 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.