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/aderaaij/loopback-training-server/claude-mdgit clone --depth 1 https://github.com/aderaaij/loopback-training-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 | $0.08389 | $0.08389 |
| Opus 5 | $0.04195 | $0.04195 |
| Sonnet 5 | $0.01678 | $0.01678 |
| Haiku 4.5 | $0.00839 | $0.00839 |
Grade A, and why
loopback-training-server CLAUDE.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 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.
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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Training API
Personal workout tracking API with Apple Watch integration queue, training plans, health metrics, and a web dashboard.
The companion iOS app lives at aderaaij/loopback-training-app; a working copy is usually checked out as a sibling directory (../loopback-training-app). Cross-reference it for the client side of the API contract (WorkoutAPIClient.swift, SessionStore.swift, WorkoutScheduleManager.swift) before changing wire formats — and git pull it first, since development happens elsewhere.
Tech Stack
- Backend: FastAPI (Python 3.13) with Uvicorn
- Database: PostgreSQL 16 with SQLAlchemy 2.0 ORM, Alembic migrations
- Package manager: uv
- Frontend: React 19 + TypeScript SPA ("Loopback", in
frontend/) — Vite 8, React Compiler, TanStack Query, react-router, hand-rolled SVG charts, Leaflet route maps - MCP Server: FastMCP 2.0 (in
mcp/) - Infrastructure: Docker Compose (
docker-compose.yml)
Project Structure
backend/
app/
main.py # FastAPI app entry point (+ serves the SPA build, see below)
auth.py # Bearer token auth
config.py # Pydantic-settings
database.py # SQLAlchemy setup
models/ # ORM models
routes/ # API route handlers
schemas/ # Pydantic request/response schemas
migrations/ # Alembic migrations
Dockerfile # Multi-stage build: Node (frontend) + uv (backend); context = repo root
frontend/
src/
lib/ # api client, wire types, auth context, query hooks, formatters
components/ # layout, shared UI, SVG chart primitives, route map
screens/ # one file per screen (Overview, Calendar, Workouts, Plans, Notes, Health, Queue, Settings, Users)
styles/ # global design tokens + per-screen CSS
mcp/
app/
main.py # FastMCP server entry point
config.py # MCP settings
coaching/ # Coaching playbook content (core.md + goals/*.md) + loader
tools/ # MCP tool routers (workouts, queue, actions, feedback, health, plans, coaching)
services/ # HTTP client for backend API
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 · 299 lines · 8,389 tokens per session scan A ff4af9e2c211
loopback-training-server CLAUDE.md is an instructions file published in the GitHub repository aderaaij/loopback-training-server (3 stars, last pushed 1mo ago), licensed MIT. It adds 8,389 tokens to every session, about $0.0419 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
ProductFlow AGENTS.md
Instructions for yuqie6/ProductFlow, covering trellis instructions, repository guidelines, project structure & module organization, build, test, and development commands and coding style & naming conventions.
robosystems CLAUDE.md
Instructions for RoboFinSystems/robosystems, covering claude.md - robosystems development guide, critical rules, api endpoints (local testing), health check and extensions operation write (close a period).
rustzen-admin AGENTS.md
Instructions for idaibin/rustzen-admin, covering repository rules, source of truth, reading order, boundaries and working rules.
agent-stack-template AGENTS.md
Instructions for krivoox/agent-stack-template, covering this is not the next.js you know, agent guide, what this repository is, every turn and what to open after classify.
legalise AGENTS.md
Instructions for b1rdmania/legalise, covering legalise — agent context (agents.md), 1. the one-paragraph version, 2. what it's built to answer (the four questions), 3. stack (boring by design) and 4. the core concepts.
exploreyc CLAUDE.md
Instructions for KonstantinMB/exploreyc, covering claude.md, project overview, tech stack, development commands and backend dev server.