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.
git clone --depth 1 https://github.com/markmhendrickson/foundationWrote 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.
[](https://agentmods.dev/rules/markmhendrickson/foundation/security)<a href="https://agentmods.dev/rules/markmhendrickson/foundation/security"><img src="https://agentmods.dev/badge/rules/markmhendrickson/foundation/security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/markmhendrickson/foundation/security"><img src="https://agentmods.dev/badge/rules/markmhendrickson/foundation/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01297 |
| Opus 5.5 | $0.00012 | $0.00519 |
| Sonnet 5.5 | $0.00006 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Rule
Prevents accidental commits of private, sensitive, or confidential documentation and data.
Configuration: This rule uses protected paths configured in foundation-config.yaml under security.pre_commit_audit.protected_paths.
Pre-Commit Security Audit
Before staging or committing ANY changes, agents MUST perform the following checks:
1. Protected Paths Check
Check for any files in protected paths (configured in foundation-config.yaml):
# Load protected paths from config (example paths shown)
PROTECTED_PATHS=("docs/private/" "data/") # Configured per repository
# Check unstaged changes
for path in "${PROTECTED_PATHS[@]}"; do
if git status --porcelain | grep -E "^[AM]|^\?\?" | grep -qE "$path"; then
echo "❌ SECURITY VIOLATION: Files in $path detected!"
git status --porcelain | grep -E "^[AM]|^\?\?" | grep "$path"
exit 1
fi
done
# Check staged changes (if any exist)
for path in "${PROTECTED_PATHS[@]}"; do
if git diff --cached --name-only 2>/dev/null | grep -qE "$path"; then
echo "❌ SECURITY VIOLATION: Files in $path already staged!"
git diff --cached --name-only | grep "$path"
exit 1
fi
done
If any files match protected paths, ABORT the commit immediately and alert the user.
2. Environment Files Check
Check for any .env* files (should be in .gitignore but verify):
if git status --porcelain | grep -qE "\.env"; then
echo "❌ SECURITY VIOLATION: .env files detected!"
git status --porcelain | grep "\.env"
exit 1
fi
if git diff --cached --name-only 2>/dev/null | grep -qE "\.env"; then
echo "❌ SECURITY VIOLATION: .env files already staged!"
git diff --cached --name-only | grep "\.env"
exit 1
fi
If any .env* files are detected, ABORT the commit.
Configuration: Enable/disable via security.pre_commit_audit.check_env_files in foundation-config.yaml.
3. Sensitive File Pattern Check
Check for files with sensitive naming patterns:
# Check for files with "secret" or "private" in path (excluding legitimate code)
git status --porcelain | grep -vE "(test|spec|property_keys)" | grep -iE "(secret|private)" | grep -vE "$(IFS='|'; echo "${PROTECTED_PATHS[*]}")" && echo "WARNING: Suspicious file patterns detected" && exit 1
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.
- 1mo ago First seen · 159 lines · 31 tokens per session scan A 6e61331ec284
security is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,297 once invoked, about $0.0001 per session on Opus 5.5. 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.