spec-engineering

spec-engineering is a cursor rule for Cursor from Oriolshhh/runware-image-mcp. It costs 7 tokens per session (624 once invoked), scanned A, original, MIT.

A specification-writing skill that turns a request into precise requirements and tests that developers and reviewers can follow.

In plain words
What is it for?
It is used to document goals, non-goals, assumptions, APIs, user-interface states, edge cases, rollout details, and requirement-linked tests.
Why use it?
It removes guesswork when requirements are incomplete, unclear, or disputed.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents.

Good fit It is used to document goals, non-goals, assumptions, APIs, user-interface states, edge cases, rollout details, and requirement-linked tests.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/oriolshhh/runware-image-mcp/spec-engineering
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.

Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

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 spec-engineering

README.md
[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/spec-engineering/github.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/spec-engineering)
Your own site
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/spec-engineering"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/spec-engineering/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-engineering

Your own site · 80×15
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/spec-engineering"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/spec-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 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 $0.00007 $0.00624
Opus 5 $0.00003 $0.00312
Sonnet 5 $0.00001 $0.00125
Haiku 4.5 $0.00001 $0.00062

Measured 5d ago against content hash 7115b9ba54b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spec-engineering 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.

.cursor/rules/spec-engineering.mdc · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: spec-engineering

Spec Engineering

Purpose

Convert a request into a precise, testable specification that a reviewer can approve and an implementer can follow without guessing.

When to use it

  • Any non-trivial change, new feature, or behavior change.
  • When requirements are ambiguous or stakeholders disagree.

Instructions

  1. Read fresh repository context and relevant source before asking questions.
  2. Ask one batch of at most three decision-changing questions (five only when unavoidable); state safe defaults for non-blocking ambiguity.
  3. Choose direct-spec, specialist-assisted-spec, or full-council-spec from complexity, reversibility, cross-cutting scope, security, and product risk.
  4. For specialist-assisted planning, select only relevant reviewers and gather separate evidence-backed reports, parallelizing only with native isolated agents. Use /council for the full-council path.
  5. Capture background, user stories, explicit non-goals, assumptions, and any meaningful specialist disagreement.
  6. Write numbered, testable requirements and map tests to each requirement.
  7. Describe data/API changes, UI/UX states, compatibility, rollout, and edge cases.
  8. Break work into dependency-aware tasks. Each task names its owner role, requirement IDs, dependencies, ownership area, acceptance criteria, tests, parallelizability, and integration point.
  9. Save to .agent/specs/<kebab-case-name>.md and request approval.
  10. Include the /spec frontmatter contract and keep status/revision metadata synchronized when the document changes.

Output format

A single Markdown spec with: title, goal, background, user stories, requirements, non-goals, UI/UX notes, data and API changes, edge cases, test plan, planning path and consultations, implementation tasks, review checklist, open questions.

Anti-patterns

  • Vague requirements that cannot be verified.
  • Silent assumptions instead of explicit open questions.
  • Asking the user for information available in repository context.
  • Invoking every specialist regardless of relevance.
  • Calling simulated role passes independent subagents.
  • Marking tasks parallelizable despite shared files or unresolved dependencies.
  • Starting implementation before approval.

Read the full file on GitHub · 64 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. 5d ago First seen · 64 lines · 7 tokens per session scan A 7115b9ba54b1

Subscribe to this mod's changes

spec-engineering is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 624 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 2026-09-03.