risk-factors

risk-factors is a cursor rule for coding agents from andyzengmath/soliton. It costs 0 tokens per session (299 once invoked), scanned A, original, MIT.

Definitions and weights for scoring the risk of pull-request changes before review agents are assigned.

In plain words
What is it for?
Use it to calculate a risk level for a pull request and decide which review checks or agents should be used.
Why use it?
It makes review decisions consistent by measuring factors such as change size, complexity, sensitive files, affected code, and missing tests.

Cursor rule

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 rules/andyzengmath/soliton/risk-factors
Clone the repo
git clone --depth 1 https://github.com/andyzengmath/soliton

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 risk-factors

README.md
[![agentmods](https://agentmods.dev/badge/rules/andyzengmath/soliton/risk-factors.svg)](https://agentmods.dev/rules/andyzengmath/soliton/risk-factors)
Your own site
<a href="https://agentmods.dev/rules/andyzengmath/soliton/risk-factors"><img src="https://agentmods.dev/badge/rules/andyzengmath/soliton/risk-factors.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 299 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 $0.00000 $0.00299
Opus 5 $0.00000 $0.00150
Sonnet 5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured 4d ago against content hash 025d8bb70ef6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

risk-factors 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.

rules/risk-factors.mdc · 30 lines

What it actually says

Risk Scoring Factors

Invariant: Factor weights must sum to 100%. Current total: 25 + 20 + 20 + 15 + 10 + 10 = 100%.

Factors

Factor Weight Scoring
Blast radius 25% min(100, importerCount * 10)
Change complexity 20% controlFlowLines / totalAddedLines * 100
Sensitive paths 20% 100 if any match, 0 otherwise
File size/scope 15% <50 lines=10, 50-200=30, 200-500=60, 500-1000=80, >1000=100
AI-authored signals 10% Weighted sum of detected signals
Test coverage gap 10% (gapFiles / totalProdFiles) * 100

Risk Levels

Level Score Agents Dispatched
LOW 0-30 correctness, consistency
MEDIUM 31-60 + security, test-quality
HIGH 61-80 + hallucination, cross-file-impact
CRITICAL 81-100 + historical-context
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 · 30 lines · 0 tokens per session scan A 025d8bb70ef6

Subscribe to this mod's changes

risk-factors is a cursor rule published in the GitHub repository andyzengmath/soliton (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 299 tokens. 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.

Related

Other cursor rules, from other repositories

openehr-context

When working with openEHR (archetypes, templates, AQL, ADL, CKM, compositions), load guides from the MCP server before answering or editing.

Cadasto/openehr-assistant-plugin · 0 tokens

cursor

Always-on my-adhd-caveman. Off with "stop adhd-caveman" or "normal mode".

SteinsFu/my-adhd-caveman · 240 tokens

delta-briefing

Make a recurring brief report what changed since the last edition instead of restating everything. Use when a weekly or monthly report keeps repeating itself, when setting up a scheduled monitor or digest, or when asked to make a recurring update delta-aware. Produces a changes-first brief plus the state record the…

mohitagw15856/pm-claude-skills · 65 tokens

voice-agent-design

Design a voice AI agent for phone or in-app conversations — call flows, interruption handling, escalation to humans, and the metrics that catch a bad voice experience. Use when asked to design a voice agent, automate a phone line, spec an IVR replacement, or review why callers hate an existing voice bot. Produces a…

mohitagw15856/pm-claude-skills · 95 tokens

ai-content-audit

Audit a content library, docs site, or blog for AI-generated filler that's eroding trust and search performance — and triage what to fix, rewrite, or delete. Use when asked to find slop in a content library, audit AI-written content quality, explain why content engagement or rankings dropped after scaling with AI, or…

mohitagw15856/pm-claude-skills · 132 tokens

investor-update

Write a structured monthly or quarterly investor update. Use when asked to write an investor update, investor newsletter, board update, or startup progress report for investors. Produces a clear, credible update with highlights, metrics, challenges, and asks — in the format investors actually want to read.

mohitagw15856/pm-claude-skills · 57 tokens