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.
npx agentmods add rules/markmhendrickson/foundation/documentation_rulesgit clone --depth 1 https://github.com/markmhendrickson/foundationWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00020 | $0.01151 |
| Opus 5 | $0.00010 | $0.00575 |
| Sonnet 5 | $0.00004 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
documentation_rules 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Rules
Rules for creating and maintaining documentation files to minimize context window usage while maintaining clarity.
Core Principles
Minimize context usage: Every word, section, and file consumes context. Remove anything that doesn't directly serve the reader's immediate need.
Single source of truth: Each concept, rule, or process documented once. Reference, don't duplicate.
Concise language: Use the shortest clear phrasing. Prefer direct statements over explanations.
Content Rules
Avoid Redundancy
Within files:
- Don't repeat the same rule in multiple sections
- Don't restate the title in the first paragraph
- Don't summarize what you're about to say before saying it
Between files:
- Don't duplicate rules across multiple files
- Reference other files instead of copying content
- If overlap exists, consolidate into one file and reference it
Examples:
- Bad: "This document defines requirements. The requirements are defined below."
- Good: "Requirements:"
Remove Unnecessary Elements
Don't include:
- "Related Documentation" sections (use file structure and naming for discovery)
- Meta properties (Status, Last Updated, Related) in file headers
- Separator lines (
---) unless grouping distinct sections - Empty lines between every section (use sparingly)
- Introductory paragraphs that restate the title
- "Purpose" sections that repeat the filename
- Closing summaries that restate what was said
Do include:
- Direct statements of rules or requirements
- Essential context only
- Examples when they clarify ambiguity
Language Conciseness
Use:
- Direct commands: "Do X" not "Agents should do X" or "It is recommended that agents do X"
- Short phrases: "Required" not "This is a mandatory requirement"
- Active voice: "Create file" not "File should be created"
- Lists over paragraphs when possible
- Specific terms over general ones
Avoid:
- Hedging language: "should", "may", "consider" (use "must" or "do not")
- Filler phrases: "in order to", "for the purpose of", "it is important to note"
- Redundant qualifiers: "very important", "absolutely required"
- Explanatory preambles: "The reason for this is..." (state the rule, not why it exists unless critical)
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.
- yesterday First seen · 167 lines · 20 tokens per session scan A f29fe31b55a6
documentation_rules is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,151 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.