decision-synthesis

decision-synthesis is a cursor rule for Cursor from Oriolshhh/runware-image-mcp. It costs 14 tokens per session (490 once invoked), scanned A, original, MIT.

A decision-making method for combining independent reviews and objections into one honest recommendation while keeping minority views and unknowns visible.

In plain words
What is it for?
It is used to compare options against criteria such as risk, effort, value, and reversibility, then record the recommendation and conditions that could change it.
Why use it?
It prevents disagreement from being averaged away and stops the decision record from claiming evidence that reviewers did not provide.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It is used to compare options against criteria such as risk, effort, value, and reversibility, then record the recommendation and conditions that could change it.

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

README.md
[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/decision-synthesis.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/decision-synthesis)
Your own site
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/decision-synthesis"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/decision-synthesis.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 $0.00014 $0.00490
Opus 5 $0.00007 $0.00245
Sonnet 5 $0.00003 $0.00098
Haiku 4.5 $0.00001 $0.00049

Measured 4d ago against content hash 8cb0d73d55db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

decision-synthesis 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 4d 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/decision-synthesis.mdc · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: decision-synthesis

Decision Synthesis

Purpose

Combine independent reviews into a single, honest recommendation that a human can approve — without averaging away disagreement or inventing support.

When to use it

  • At the synthesis step of /council, after independent reports and one rebuttal round.
  • Whenever several reviewers' inputs must become one decision.

Instructions

  1. Restate the decision and the criteria (correctness, value, complexity, risk, reversibility, effort) before comparing options.
  2. Synthesize by argument strength and evidence, not by counting votes.
  3. Compare the leading option and at least one alternative against the criteria, citing the specific report behind each judgment.
  4. Preserve dissent: record minority positions and the conditions under which they would win.
  5. Assess how independent the deliberation actually was (parallel, sequential, or simulated) and let that cap the stated confidence.
  6. Use only evidence present in the reports; mark gaps as unknowns rather than filling them.

Output format

A decision record: recommended path, confidence (with deliberation mode), criteria and scoring, rejected alternatives (with the reason each lost), key risks and mitigations, preserved dissent, unresolved questions, and the next step (/spec after human approval).

Anti-patterns

  • Voting or averaging instead of weighing evidence.
  • Hiding dissent to manufacture consensus.
  • Inventing evidence absent from the reports.
  • Overstating confidence when deliberation was simulated, not independent.

Verification checklist

  • Criteria are stated and options scored against them with citations.
  • Every claim traces to a specialist report; gaps are marked unknown.
  • Dissent and the deliberation mode are recorded; confidence reflects them.
  • The record ends at the human-approval gate.

Read the full file on GitHub · 54 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. 4d ago First seen · 54 lines · 14 tokens per session scan A 8cb0d73d55db

Subscribe to this mod's changes

decision-synthesis is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 490 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.