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/sethdford/flowx/workflow-rulesgit clone --depth 1 https://github.com/sethdford/flowxWhat 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 | $0.00000 | $0.02566 |
| Opus 5 | $0.00000 | $0.01283 |
| Sonnet 5 | $0.00000 | $0.00513 |
| Haiku 4.5 | $0.00000 | $0.00257 |
Grade A, and why
workflow-rules scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ 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 โ 316 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow Rules: Catch Issues Early
๐จ BEFORE ANY CODE CHANGES
1. Run Quality Checks
# ALWAYS run these before starting work
npm run lint:check # Check current issues
npm run typecheck # Verify TypeScript
npm run build # Ensure builds
npm test # Run tests
# Check our performance metrics
time node dist/cli.js --version # Should be <50ms
du -sh dist/ # Should be <5MB
2. Check File Sizes (Current Issues Found)
# Files over 250 lines need splitting:
# โ ๏ธ src/ui/utils/markdownUtilities.ts has 414 lines
# โ ๏ธ src/ui/hooks/useClaudeStream.ts has 390 lines
# โ ๏ธ src/ui/hooks/useClaude4Stream.ts has 467 lines
# โ ๏ธ src/tools/screenshot.ts has 417 lines
# โ ๏ธ src/tools/code-analyzer.ts has 291 lines
find src -name "*.ts" -exec wc -l {} + | awk '$1 > 250 {print "โ ๏ธ " $2 " has " $1 " lines"}'
3. Check Console Pollution (Current Issue: 278 statements!)
# We have 278 console statements outside CLI/tests - need cleanup!
grep -r "console\." src/ | grep -v ".test." | grep -v "cli.ts" | wc -l
# Find specific violations:
grep -rn "console\." src/ | grep -v ".test." | grep -v "cli.ts" | head -20
๐ง DEVELOPMENT PATTERNS
File Creation Rules
// โ
CORRECT - New file template
/**
* [Module Name] - [Brief Description]
*
* [Detailed description of purpose and functionality]
*/
import { /* required imports */ } from './path.js'; // Always .js extension
import type { /* type imports */ } from './types.js';
// Implementation (max 250 lines)
export { /* exports */ };
Function Creation Rules
// โ
CORRECT - Function template (max 30 lines)
/**
* [Function description]
*
* @param parameter - Description
* @returns Description
* @throws {UserError} When [condition]
*/
async function descriptiveFunctionName(
parameter: SpecificType
): Promise<SpecificReturnType> {
// Validation
if (!isValid(parameter)) {
throw createUserError('Clear error message', {
category: ErrorCategory.VALIDATION,
resolution: 'How to fix this'
});
}
// Implementation (max 25 lines after validation)
try {
const result = await operation(parameter);
return result;
} catch (error) {
throw createUserError('Operation failed', {
category: ErrorCategory.SYSTEM,
details: { error }
});
}
}
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 ยท 316 lines ยท 0 tokens per session scan A 0cd8518388b1
workflow-rules is a cursor rule published in the GitHub repository sethdford/flowx (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,566 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.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
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.
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.