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/readykit/agents-mdgit clone --depth 1 https://github.com/level09/readykitWhat 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 | $0.01836 | $0.01836 |
| Opus 5 | $0.00918 | $0.00918 |
| Sonnet 5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
readykit AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await axios.get('/api/items'); How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Context for AI agents working with ReadyKit, a Flask SaaS template with multi-tenant workspaces.
Stack
- Backend: Flask 3.1, SQLAlchemy 2.x, Flask-Security-Too
- Frontend: Vue 3 + Vuetify 3 (no build step, loaded from static/)
- Database: PostgreSQL (production), SQLite (dev)
- Auth: Email/password, OAuth (Google, GitHub), 2FA, WebAuthn
- Billing: Stripe or Chargebee (via
BILLING_PROVIDERenv var) - Package Manager: uv
Commands
./setup.sh # First-time setup
uv run flask create-db # Initialize database (stamps migrations head)
uv run flask install # Create admin user
uv run flask run # Dev server on :5000
uv run flask db migrate -m "" # Draft migration from model changes
uv run flask db upgrade # Apply pending migrations
uv run ruff check --fix . # Lint
uv run ruff format . # Format
docker compose up --build # Production stack
Database Migrations
Schema changes use Alembic (Flask-Migrate). Autogenerate is a draft generator, not a source of truth: always review and hand-edit the generated revision before applying it. Complex changes (data backfills, column renames) should be written by hand in the revision file.
uv run flask db migrate -m "add status to workspace" # Draft
# Review migrations/versions/<revision>.py, adjust
uv run flask db upgrade # Apply
Fresh databases: create-db builds the schema and stamps head automatically.
Databases that predate migrations: run uv run flask db stamp head once.
Project Structure
enferno/
├── app.py # Application factory
├── settings.py # Single Config class (env-based)
├── extensions.py # Flask extensions (db, cache, mail, session)
├── public/views.py # Landing, login, register (no auth)
├── portal/views.py # Dashboard, workspace routes (authenticated)
├── user/
│ ├── views.py # Superadmin CMS (user management)
│ └── models.py # User, Workspace, Membership, etc.
├── api/webhooks.py # Stripe/Chargebee webhooks
├── services/
│ ├── workspace.py # Multi-tenant: WorkspaceService, require_workspace_access
│ ├── billing.py # HostedBilling, requires_pro_plan
│ └── auth.py # OAuth handlers
├── static/js/config.js # Vue config with custom delimiters
└── templates/ # All Jinja2 templates (single directory)
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 · 274 lines · 1,836 tokens per session scan A 86a2cf2f1257
readykit AGENTS.md is an instructions file published in the GitHub repository level09/readykit (246 stars, last pushed 5d ago), licensed MIT. It adds 1,836 tokens to every session, about $0.0092 per session on Opus 5. A static security scan graded it A with 1 finding (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
openalgo CLAUDE.md
Claude Code instructions for marketcalls/openalgo, covering claude.md, documentation map, skills, security and deployment model and runtime constraints.
django-starter-template AGENTS.md
Instructions for wilfredinni/django-starter-template, covering agents.md, commands, lint & typecheck, architecture and testing.
enferno AGENTS.md
Instructions for level09/enferno, covering agents.md, framework overview, project structure, development commands and setup & installation.
robs_awesome_python_template AGENTS.md
Instructions for tedivm/robs_awesome_python_template, covering agent instructions and key technologies.
Netskrafl CLAUDE.md
Claude Code instructions for mideind/Netskrafl, covering claude.md, project overview, common development commands, development setup and install python dependencies.
blogman CLAUDE.md
Instructions for CrazyWillBear/blogman, covering claude.md, rules, layout and conventions.