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/jenreh/appkit-bpmn-server/pythongit clone --depth 1 https://github.com/jenreh/appkit-bpmn-serverWhat 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 | $0.01740 | $0.01740 |
| Opus 5 | $0.00870 | $0.00870 |
| Sonnet 5 | $0.00348 | $0.00348 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
appkit-bpmn-server python.instructions.md 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 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Development Instructions
Project Overview
This is a Python 3.13 project using:
- Reflex - Web framework for building reactive UIs
- FastAPI - High-performance web framework
- SQLAlchemy 2.0 - Database ORM
- Alembic - Database migrations
- Pydantic - Data validation
- uv - Package and project manager
Setup and Installation
# Install dependencies
make install
# or
uv sync
Development Workflow
Running the Application
# Start development server
make reflex
# or
uv run reflex run
# Start with debug logging
make reflex-debug
# or
uv run reflex run --loglevel=debug
# Production mode
make reflex-prod
# or
uv run reflex run --env prod
Testing
# Run tests
make test
# or
uv run pytest
# Run tests with coverage
uv run pytest --cov=app --cov=appkit_assistant --cov=appkit_commons --cov=appkit_imagecreator --cov=appkit_mantine --cov=appkit_ui --cov=appkit_user
Note: Tests should be written in tests/ directory following the pattern test_*.py.
Linting and Formatting
# Check code style
make check
# or
uv run ruff check .
uv run ruff format --check .
# Auto-fix linting issues
make lint
# or
uv run ruff check --fix .
# Format code
make format
# or
uv run ruff format .
uv run ruff check --fix .
Database Migrations
# Check current migration status
make alembic
# or
uv run alembic current
# Apply migrations
make db-migrate
# or
uv run alembic upgrade head
# View migration history
make db-migrate-history
# or
uv run alembic history
# Rollback one migration
make db-migrate-down
# or
uv run alembic downgrade -1
Code Style Guidelines
Logging
CRITICAL: Never use f-strings in logger calls. Use string formatting with parameters instead.
import logging
log = logging.getLogger(__name__)
# ✅ CORRECT
log.info("Loaded items: %d", count)
log.error("Failed to process user: %s", user_id)
log.debug("Processing request with params: %s, %s", param1, param2)
# ❌ INCORRECT - DO NOT USE
log.info(f"Loaded items: {count}")
log.error(f"Failed to process user: {user_id}")
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 · 316 lines · 1,740 tokens per session scan A d29fd2588a94
appkit-bpmn-server python.instructions.md is an instructions file published in the GitHub repository jenreh/appkit-bpmn-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,740 tokens to every session, about $0.0087 per session on Opus 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 instructions, from other repositories
google-search-console-mcp CLAUDE.md
Instructions for FlorianBruniaux/google-search-console-mcp, covering claude.md, docs, commands, requires python 3.11+ and install (dev mode with test deps).
resonite-mcp AGENTS.md
Instructions for sandraschi/resonite-mcp, covering resonite mcp — agents.md, quick start, frontend at http://localhost:10978 (via websota/start.ps1), architecture and tool categories.
swag-mcp CLAUDE.md
Instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.
unifi-fabric-mcp-server CLAUDE.md
Instructions for swkstudios/unifi-fabric-mcp-server, covering claude.md — unifi fabric mcp server, what this repo is, pass-through invariant (do not break this), project structure and development setup.
gurume AGENTS.md
Instructions for narumiruna/gurume, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
ai-producer-hub AGENTS.md
Instructions for sandraschi/ai-producer-hub, covering ai-producer-hub agent context and quick ref.