GrowthLint
AGENTS.md2 starsChanged 8 months agoMITView on GitHub
Guidelines for AI agents working in this repository. This repository contains GrowthLint — a growth marketing linter with both a Python CLI and AI agent skills. The CLI handles deterministic scanning (rules, scoring, reports). The skills layer adds qualitative AI analysis on top. Skills live in .claude/skills/ and each wraps the Python CLI with AI intelligence: Rules are YAML files in growthlint/data/. Each rule has: - id, name, category, severity (critical/warning/info) - check block with type (presence/absence/count/pattern/attribute/analytics/meta_quality) - impact description…
- Installs packages
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository12 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- check-integrationsSkill
- check-seoSkill
- compare-sitesSkill
- find-dead-linksSkill
- find-revenue-leaksSkill
- generate-analytics-specSkill
- growth-auditSkill
- growth-diffSkill
- map-funnelSkill
- suggest-schemaSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 77
Run Python CLI commands via shell
- Very specific: line 78
Read SKILL.md files for skill instructions
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
Guidelines for AI agents working in this repository.
Repository Overview
This repository contains GrowthLint — a growth marketing linter with both a Python CLI and AI agent skills. The CLI handles deterministic scanning (rules, scoring, reports). The skills layer adds qualitative AI analysis on top.
- Name: GrowthLint
- GitHub: super0510/GrowthLint
- License: MIT
Repository Structure
growthlint/
├── .claude/
│ └── skills/ # Claude Code skills (10 skills)
│ └── skill-name/
│ └── SKILL.md
├── .claude-plugin/
│ └── marketplace.json # Claude Code plugin manifest
├── growthlint/ # Python CLI package
│ ├── scanners/ # URL, repo, sitemap, DOM parsing
│ ├── rules/ # YAML rule engine + loader
│ ├── reporters/ # Markdown, JSON, CSV output
│ ├── analyzers/ # Dead links, integrations, psychology, schema
│ ├── generators/ # Funnel maps, analytics specs, patches, diffs
│ ├── data/ # 45+ YAML rules (8 files)
│ ├── cli.py # Typer CLI entry point
│ ├── models.py # Pydantic data models
│ └── ci.py # CI/CD threshold checks
├── tests/ # 120+ tests
├── examples/ # Sample output files
├── CONTRIBUTING.md
├── LICENSE
└── README.mdSkills
Skills live in .claude/skills/ and each wraps the Python CLI with AI intelligence:
| Skill | CLI Command | AI Adds |
| growth-audit | growthlint scan | Page psychology, prioritized action plan |
| find-revenue-leaks | growthlint scan | Dollar estimates, implementation priorities |
| check-seo | growthlint scan --categories seo | Content depth analysis, internal linking |
| generate-analytics-spec | growthlint generate-spec | Code snippets, QA checklist |
| map-funnel | growthlint map-funnel | A/B test ideas, benchmarks |
| compare-sites | growthlint compare | Qualitative trust/messaging comparison |
| check-integrations | growthlint check-integrations | Conflict analysis, stack recommendations |
| find-dead-links | growthlint check-links | Pattern detection, SEO impact |
| suggest-schema | growthlint suggest-schema | Complete JSON-LD, SERP preview |
| growth-diff | growthlint diff | Velocity assessment, trajectory analysis |
Development
pip install -e .
python -m pytest tests/ -vRules
Rules are YAML files in growthlint/data/. Each rule has:
id,name,category,severity(critical/warning/info)checkblock withtype(presence/absence/count/pattern/attribute/analytics/meta_quality)impactdescription andfixrecommendationrevenue_weight(0.0-1.0) for scoring
See CONTRIBUTING.md for the full rule writing guide.
Agent Compatibility
This repository works with any agent that can:
- Run Python CLI commands via shell
- Read SKILL.md files for skill instructions
Skills are in standard markdown format compatible with Claude Code, Cursor, Windsurf, and any agent supporting the skills pattern.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

