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 instructions/level09/enferno/agents-mdgit clone --depth 1 https://github.com/level09/enfernoWhat 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 | $0.06870 | $0.06870 |
| Opus 5 | $0.03435 | $0.03435 |
| Sonnet 5 | $0.01374 | $0.01374 |
| Haiku 4.5 | $0.00687 | $0.00687 |
Grade C, and why
enferno AGENTS.md scanned grade C with 2 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
&& rm -rf /var/lib/apt/lists/* Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
axios.post('/api/endpoint', data, { How it starts
The opening of the file, as written. The whole thing — 1,128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides comprehensive architectural patterns and coding standards for AI agents working with the Enferno framework.
Framework Overview
Enferno is a Flask-based web framework optimized for rapid development with modern tooling:
- Backend: Flask 3.x with Blueprint organization
- Frontend: Vue 3 + Vuetify (no build step required)
- Database: SQLAlchemy 2.x with modern statement-based queries
- Auth: Flask-Security-Too with 2FA, WebAuthn, OAuth support
- Tasks: Celery + Redis for background processing
- Package Manager: uv for fast dependency management
Project Structure
enferno/
├── enferno/ # Main application package
│ ├── app.py # Application factory (create_app)
│ ├── settings.py # Environment-based configuration
│ ├── extensions.py # Flask extensions initialization
│ ├── commands.py # Custom Flask CLI commands
│ ├── public/ # Public routes (no auth)
│ │ ├── views.py
│ │ ├── models.py
│ │ └── templates/
│ ├── user/ # Authentication & user management
│ │ ├── views.py
│ │ ├── models.py
│ │ ├── forms.py
│ │ └── templates/
│ ├── portal/ # Protected dashboard/admin
│ │ ├── views.py
│ │ └── templates/
│ ├── services/ # Business logic layer
│ ├── tasks/ # Celery task definitions
│ ├── utils/ # Utility functions
│ ├── static/ # CSS, JS, images
│ │ ├── css/
│ │ ├── js/
│ │ └── img/
│ └── templates/ # Global Jinja2 templates
├── docs/ # Documentation
├── nginx/ # Nginx configuration
├── instance/ # Instance-specific files (gitignored)
├── pyproject.toml # Dependencies and project metadata
├── uv.lock # Lock file for reproducible installs
├── .env # Environment variables (gitignored)
├── .env-sample # Environment template
├── setup.sh # Setup script
├── run.py # Application entry point
├── Dockerfile # Docker configuration
└── docker-compose.yml # Docker Compose orchestration
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.
- 2d ago First seen · 1,128 lines · 6,870 tokens per session scan C 04956000f917
enferno AGENTS.md is an instructions file published in the GitHub repository level09/enferno (569 stars, last pushed 6d ago), licensed MIT. It adds 6,870 tokens to every session, about $0.0343 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
NewsBlur AGENTS.md
AGENTS.md instructions for samuelclay/NewsBlur, covering newsblur development guidelines, planning & clarification, debugging, bug fixing workflow and git branching.
Chat2DB AGENTS.md
AGENTS.md instructions for OtterMind/Chat2DB, covering chat2db community agent contract, context, product invariants, repository map and structural code navigation.
interview-guide AGENTS.md
AGENTS.md instructions for Snailclimb/interview-guide, covering ai interview platform agent rules, tech stack, commands, project structure and architecture.
interview-guide CLAUDE.md
Claude Code instructions for Snailclimb/interview-guide, covering claude code instructions, path rules and maintenance.
NewsBlur CLAUDE.md
Claude Code instructions for samuelclay/NewsBlur, a project described as: NewsBlur is a personal news reader that brings people together to talk about the world. A new sound of an old instrument.
mcp-data-analysis-agent copilot-instructions.md
Copilot instructions for hassanvfx/mcp-data-analysis-agent, covering clineflow: okf knowledge workflow, chatgpt codex and compatible agents, task knowledge rules, commit workflow and knowledge navigation.