risk_management

Rules that make a coding agent stop and ask a person before high-risk changes, such as database structure, security, or architecture changes.

In plain words
What is it for?
Controlling approval points for schema, authentication, architectural, and foundation-document changes using project configuration.
Why use it?
It adds a human approval step before edits that could affect system stability or security.

Cursor rule for Cursor

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/markmhendrickson/foundation/risk_management
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/foundation

Made for: Cursor.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 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 $0.00030 $0.01046
Opus 5 $0.00015 $0.00523
Sonnet 5 $0.00006 $0.00209
Haiku 4.5 $0.00003 $0.00105

Measured yesterday against content hash 5b9da427646d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

risk_management 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 yesterday.

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/risk_management.mdc · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Risk Management and Hold Points Rule

Reference: foundation/conventions/documentation_standards.md - Documentation standards

Purpose

Ensures agents stop and request human approval for high-risk changes that could impact system stability, security, or architectural integrity.

Scope

This document defines:

  • When agents MUST stop and request approval
  • Risk levels (Low/Medium/High)
  • Hold point triggers
  • Approval workflow

This document does NOT cover:

  • Specific constraints agents must enforce (see agent_constraints.md)
  • Security audit requirements (see security.md)
  • Repository-specific risk classification (configured in foundation-config.yaml)

Configuration

Configure risk classification in foundation-config.yaml:

risk_management:
  enabled: true
  risk_classification_path: "docs/private/governance/risk_classification.md"  # Optional
  foundation_docs_path: "docs/foundation/"  # Path to foundation documents
  high_risk_paths: []  # Repository-specific high-risk paths
    # Example:
    # - "docs/foundation/"
    # - "src/auth/"

When Agents MUST Stop

AI assistants MUST stop and request human approval for:

  1. Schema changes (table structure, breaking data model changes)
  2. High-risk changes (see configured risk classification path if exists)
  3. Foundation document changes (files in configured foundation docs path)
  4. Security changes (auth, access control, encryption)
  5. Violating documented constraints (even if user requests)

Risk Levels

Low Risk

  • Documentation updates
  • UI text changes
  • Unit test additions
  • Non-breaking API additions
  • Feature additions within existing scope

Action: Proceed with standard validation checklist

Medium Risk

  • New features within scope
  • API endpoint additions
  • Logic changes in non-critical paths
  • Subsystem modifications
  • Configuration changes

Action: Proceed with enhanced validation, notify user of scope

High Risk

  • Schema migrations
  • Auth changes
  • Breaking API changes
  • Foundation document modifications (files in configured foundation docs path)
  • Security changes
  • Architectural changes
  • Changes that violate documented constraints

Read the full file on GitHub · 168 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. yesterday First seen · 168 lines · 30 tokens per session scan A 5b9da427646d

Subscribe to this mod's changes

risk_management is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,046 once invoked, about $0.0002 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.