requirements-triage

requirements-triage is a cursor rule for Cursor from Oriolshhh/runware-image-mcp. It costs 15 tokens per session (513 once invoked), scanned A, original, MIT.

A requirements-analysis skill that separates verified facts, assumptions, preferences, and blockers in a vague request.

In plain words
What is it for?
It is used to create a short decision brief with the problem, goal, evidence, defaults, and grouped clarification questions.
Why use it?
It prevents teams from debating guesses as if they were facts and focuses questions on decisions that would change the outcome.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It is used to create a short decision brief with the problem, goal, evidence, defaults, and grouped clarification questions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/oriolshhh/runware-image-mcp/requirements-triage
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 requirements-triage

README.md
[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/requirements-triage/github.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/requirements-triage)
Your own site
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/requirements-triage"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/requirements-triage/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 requirements-triage

Your own site · 80×15
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/requirements-triage"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/requirements-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 513 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 $0.00015 $0.00513
Opus 5 $0.00008 $0.00257
Sonnet 5 $0.00003 $0.00103
Haiku 4.5 $0.00002 $0.00051

Measured 5d ago against content hash 2689596511d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

requirements-triage 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/requirements-triage.mdc · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: requirements-triage

Requirements Triage

Purpose

Turn a vague request into a structured brief so downstream work argues about the right problem instead of re-deriving it.

When to use it

  • At the start of /council discovery, or before any non-trivial spec.
  • Whenever a request mixes facts, guesses, and preferences.

Instructions

  1. Restate the underlying problem in one or two sentences.
  2. Classify every element of the request:
    • Fact — verified in the repository or stated explicitly (cite it).
    • Assumption — a reasonable default you are taking (mark safe vs. needs-confirm).
    • Preference — style/scope taste that does not change correctness.
    • Blocker — an unknown whose answer would change the recommendation.
  3. For each blocker, draft the default you would take if unanswered, and note how a different answer would change the outcome.
  4. Keep only blockers that are genuinely decision-changing; demote the rest to assumptions with stated defaults.
  5. Group the surviving questions (prefer ≤3, max 5) and ask them together.

Output format

A decision brief: problem, goal/outcome, facts (cited), assumptions (with defaults), preferences, blockers/questions (each with why-it-matters), constraints, and proposed out-of-scope.

Anti-patterns

  • Asking questions whose answers cannot change the recommendation.
  • Asking one question at a time, or exceeding the 3-5 budget without need.
  • Blurring assumptions into facts, or hiding defaults instead of stating them.
  • Blocking on a question when a safe, reversible default exists.

Verification checklist

  • Each fact has a citation; each assumption has an explicit default.
  • Every listed question would change the recommendation if answered differently.
  • Questions are grouped and within budget.
  • A reader could act on the brief without re-asking the basics.

Read the full file on GitHub · 52 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 · 52 lines · 15 tokens per session scan A 2689596511d5

Subscribe to this mod's changes

requirements-triage is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 513 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 2026-09-03.