agent_constraints

A repository rule for enforcing fixed requirements, forbidden patterns, and validation checks when work affects areas such as architecture, data, or security.

In plain words
What is it for?
It helps validate work against configured repository rules, communication standards, project constraints, and a validation checklist.
Why use it?
It makes important project constraints visible during implementation and review, reducing violations and missed checks.

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

Made for: Cursor.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,950 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 $0.00027 $0.01950
Opus 5 $0.00014 $0.00975
Sonnet 5 $0.00005 $0.00390
Haiku 4.5 $0.00003 $0.00195

Measured yesterday against content hash 806f340e8c32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent_constraints 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/agent_constraints.mdc · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Constraints Rule

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

Purpose

Ensures agents enforce all absolute constraints, forbidden patterns, and validation requirements when working on the repository.

Scope

This document defines:

  • Absolute constraints that agents MUST enforce
  • Project positioning constraints (if configured)
  • Constraints agents must enforce
  • Communication constraints
  • Forbidden patterns
  • Validation checklist

This document does NOT cover:

  • Repository-specific constraints (configured in foundation-config.yaml)
  • Risk management and hold points (see risk_management.md)

Configuration

Configure project-specific constraints in foundation-config.yaml:

agent_instructions:
  enabled: true
  constraints: []  # Repository-specific constraints
    # Example:
    # - "Never violate architectural boundaries"
    # - "Always follow schema-first principles"
    # - "Enforce immutability for core data"
  validation_checklist:
    enabled: true
    custom_checks: []  # Repository-specific validation checks

Constraints are configurable per repository. Default constraints shown below can be customized or extended in foundation-config.yaml.

Absolute Constraints

Agents MUST enforce these constraints at all times (customize in foundation-config.yaml):

  1. Never violate architectural boundaries (respect layer boundaries, no cross-layer violations)
  2. Never introduce nondeterminism (no random IDs, no unstable logic, deterministic outputs)
  3. Never generate features outside project scope (stay within defined boundaries)
  4. Always follow project principles (schema-first, type-driven, or project-specific patterns)
  5. Enforce data integrity (immutability where required, proper validation)
  6. Enforce safety and explicit control (user approval where required, no implicit actions)
  7. Always output validated artifacts (code, specs, docs must pass validation)
  8. Follow project positioning (when creating marketing/content, follow project differentiators if configured)

Read the full file on GitHub · 198 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 · 198 lines · 27 tokens per session scan A 806f340e8c32

Subscribe to this mod's changes

agent_constraints is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,950 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 2026-08-31.