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/aps08/fullstack-clean-architecture/agents-mdgit clone --depth 1 https://github.com/aps08/fullstack-clean-architectureWhat 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 | $0.01733 | $0.01733 |
| Opus 5 | $0.00866 | $0.00866 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
fullstack-clean-architecture AGENTS.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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent & Project Guidelines
Welcome! This document provides commands, rules, and guidelines for developing and managing the Tempto project.
Agent Behavior Rules
These rules take highest priority and must be followed at all times.
- Keep responses short — Always give the smallest response possible unless the user explicitly asks to describe in detail (e.g., "explain", "describe", "in detail").
- No code changes on questions — If the user says "tell me", "how", asks a question with "?", or uses similar inquiry language, only answer — do not modify any code or files.
- Explain differences with tables — Whenever explaining a difference or comparison between two or more things, always use a markdown table.
🚀 Quick Commands
Frontend (web/)
- Install:
pnpm install - Development Server:
pnpm dev - Production Build:
pnpm build - Preview Build:
pnpm preview - Linting:
pnpm lint - Lint & Fix:
pnpm lint:fix - Formatting:
pnpm format - Format Check:
pnpm format:check - Unit Testing (watch):
pnpm test - Unit Testing (UI):
pnpm test:ui - Unit Testing (coverage):
pnpm test:cov - E2E Testing:
pnpm test:e2e
Backend (server/)
- Environment Sync:
uv sync - Development Server:
uv run task dev - Run Linter:
uv run task check - Run Formatter:
uv run task format - Type Checking:
uv run task type-check - Database Migrations:
- Upgrade:
uv run task upgrade(runsalembic upgrade head) - Downgrade:
uv run task downgrade(runsalembic downgrade -1)
- Upgrade:
- Testing:
uv run task test - Generate Coverage HTML Report:
uv run task cov-html(runspytest --cov=app --cov-report=html)
Backend Folder Structure (server/)
The application resides in the server/app/ directory:
core/: Core configurations, containers (dependency injection), DB connectors, standard middleware, unified exceptions, logging, security, and global dependencies.
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 · 143 lines · 1,733 tokens per session scan A cfcd95d85635
fullstack-clean-architecture AGENTS.md is an instructions file published in the GitHub repository aps08/fullstack-clean-architecture (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,733 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
netrock CLAUDE.md
Instructions for fpindej/netrock, covering claude.md, hard rules, backend, frontend and cross-cutting.
open-paper-trading-mcp CLAUDE.md
Instructions for Open-Agent-Tools/open-paper-trading-mcp, covering claude.md, project overview, essential commands, development commands and run all development tasks via the dev script.
Yuxi AGENTS.md
AGENTS.md instructions for xerrors/Yuxi, covering yuxi agent 开发约定, 每次任务先加载什么, 任务与决策, 不能破坏的系统事实 and 证据规则.
full-stack-ai-agent-template CLAUDE.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering claude.md, project overview, commands, install dependencies and run tests.
full-stack-ai-agent-template AGENTS.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering agents.md, project overview, commands, cli and architecture.
tutor-management-app CLAUDE.md
Instructions for t1112000/tutor-management-app, covering claude.md, commands, architecture, auth and page pattern.