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/rizal72/timecapsule-pi/agents-mdgit clone --depth 1 https://github.com/rizal72/TimeCapsule-PiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/rizal72/timecapsule-pi/agents-md)<a href="https://agentmods.dev/instructions/rizal72/timecapsule-pi/agents-md"><img src="https://agentmods.dev/badge/instructions/rizal72/timecapsule-pi/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.02561 | $0.02561 |
| Opus 5 | $0.01281 | $0.01281 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade B, and why
TimeCapsule-Pi AGENTS.md scanned grade B 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# Usage: sudo ./install.sh How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Guidelines for Agentic Coding Assistants
This file provides coding conventions and guidelines for TimeCapsule-Pi, a Raspberry Pi-based Time Machine backup server.
Project Overview
Technology Stack:
- Language: Bash scripting
- Configuration: INI (Samba), XML (Avahi)
- Target OS: Raspberry Pi OS (Debian-based)
- Services: Samba, Avahi
- No: build system, automated tests, package managers
Repository & Deployment:
- The repo lives ONLY on this Mac (MacBook of Riccardo)
- The Pi4 (100.124.43.88 / pi4.tail9350d7.ts.net via Tailscale) does not have the repo cloned
- Code deployed on Pi4 is applied manually or via
install.sh - SSH:
ssh [email protected](or direct IP 100.124.43.88)
Commands
No Build/Lint/Test Framework
This project uses shell scripts and configuration files. No automated build, lint, or test commands exist.
Manual Testing Commands
# Validate Samba configuration
testparm
# Check Samba version and vfs_fruit support
smbd --version
smbd -b | grep vfs_fruit
# Check service status
systemctl status smbd nmbd avahi-daemon
# Test Samba share locally
smbclient -L localhost -U username
# List available Samba shares
smbclient -L localhost -U username% -c 2>/dev/null
# Check mount point
mountpoint -q /mnt/timecapsule
df -h | grep timecapsule
# Browse Avahi services
avahi-browse -a --terminate
# Check USB drives
lsblk
lsusb
Tailscale / Remote Access
# SSH to Pi4
ssh [email protected]
# or
ssh [email protected]
# Check Samba reachable via Tailscale from Mac
nc -zv pi4.tail9350d7.ts.net 445
# Mount Time Capsule share via Tailscale
open smb://pi4.tail9350d7.ts.net/TimeCapsule
Testing Single Functions in install.sh
To test specific functions manually:
# Source the script to access functions
source ./install.sh
# Call individual functions (may require root)
check_system
detect_usb_drives
Code Style Guidelines
Shell Scripting (Bash)
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.
- 4d ago First seen · 383 lines · 2,561 tokens per session scan B d3a93399dc26
TimeCapsule-Pi AGENTS.md is an instructions file published in the GitHub repository rizal72/TimeCapsule-Pi (41 stars, last pushed 2mo ago), licensed MIT. It adds 2,561 tokens to every session, about $0.0128 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
autonomous-os AGENTS.md
AGENTS.md instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
Starcat AGENTS.md
AGENTS.md instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.
mcp-ssh-manager CLAUDE.md
Claude Code instructions for bvisible/mcp-ssh-manager, covering claude.md, project overview, architecture, commands and setup and installation.