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/ronnycoding/my-personal-assistant/claude-mdgit clone --depth 1 https://github.com/ronnycoding/my-personal-assistantWrote 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/ronnycoding/my-personal-assistant/claude-md)<a href="https://agentmods.dev/instructions/ronnycoding/my-personal-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/ronnycoding/my-personal-assistant/claude-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 | $0.02054 | $0.02054 |
| Opus 5 | $0.01027 | $0.01027 |
| Sonnet 5 | $0.00411 | $0.00411 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade B, and why
my-personal-assistant CLAUDE.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 3d 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.
- Verify: `sudo systemsetup -gettimezone` How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
Personal AI assistant for macOS productivity automation via AppleScript skills. Dual-platform support: Claude Code (skill-based) and Gemini CLI (command-based). Key domains: email management (Apple Mail), calendar intelligence (macOS Calendar), task orchestration (Reminders), and personal finance (Jupyter notebooks).
Key Commands
Testing
# Run all AppleScript tests
./tests/framework/run_tests.sh
# Test specific domain
./tests/framework/run_tests.sh --domain apple-mail
# Verify macOS permissions
./tests/framework/verify_permissions.sh
# Test individual skill
osascript .claude/skills/scan-inbox/scripts/scan_inbox.scpt 24 false
osascript .claude/skills/read-calendar/scripts/read_events.scpt "2025-10-26" "2025-10-26"
osascript .claude/skills/list-reminders/scripts/list_tasks.scpt
Finance Commands
# Extract transactions from PDFs
cd .claude/finance-notebooks
python extract_pdf_statements.py ~/Documents/Finance/*.pdf -o output.csv
# Consolidate multiple CSV files
python consolidate_statements.py ~/Documents/Finance/*.csv -o combined.csv
# Finance command workflow (via Claude Code)
/finance init --notebook="2025-budget"
/finance import --source="transactions.csv" --type="checking"
/finance analyze --type=overview
/finance advise --focus="savings"
Architecture
Dual-Platform Design
Claude Code (.claude/):
- Skill-based architecture with SKILL.md files
- Scripts distributed in skill directories
- Complex workflow orchestration
- Best for: Multi-step tasks, agent coordination
Gemini CLI (.gemini/):
- TOML command files with embedded instructions
- Centralized scripts in
.gemini/scripts/ - Flat, self-contained structure
- Best for: Quick commands, CLI workflows
Shared Components: Both use identical AppleScript implementations - only invocation differs.
Core System Flow
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.
- 3d ago First seen · 312 lines · 2,054 tokens per session scan B ee8c34d88241
my-personal-assistant CLAUDE.md is an instructions file published in the GitHub repository ronnycoding/my-personal-assistant (12 stars, last pushed 10mo ago), licensed MIT. It adds 2,054 tokens to every session, about $0.0103 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 2026-09-02.
Other instructions, from other repositories
spellbook AGENTS.md
AGENTS.md instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
codemark GEMINI.md
Gemini CLI instructions for DanielCardonaRojas/codemark, covering development workflow and debugging with the tui logging system.
vrchat-mcp AGENTS.md
AGENTS.md instructions for BASIC-BIT/vrchat-mcp, covering agents, tool ergonomics goals (distilled), curated output philosophy, specific notes (current direction) and caching considerations (planned).
minimalist copilot-instructions.md
Instructions for DivyeshJayswal/minimalist, covering minimalist (coding tasks), persistence, fast path, bias and output.
totem AGENTS.md
AGENTS.md instructions for mmnto-ai/totem, covering totem: agent instructions, what totem is, session start protocol (mandatory), essentials and totem workflow.
front-mcp CLAUDE.md
Claude Code instructions for wearehoust/front-mcp, a project described as: Secure MCP server for Front.com: search conversations, manage contacts, send messages, automate inbox workflows — 26 tools, 172 actions.