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 commands/ronnycoding/my-personal-assistant/inboxgit clone --depth 1 https://github.com/ronnycoding/my-personal-assistantWhat 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 | $0.00000 | $0.01764 |
| Opus 5 | $0.00000 | $0.00882 |
| Sonnet 5 | $0.00000 | $0.00353 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
inbox 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Intelligence Command
Scan Apple Mail inbox for the last 48 hours and extract actionable intelligence with professional context awareness, focusing on job opportunities, urgent items, and time-sensitive requests.
Phase 1: Data Collection
Execute the email scanning script to gather inbox data:
osascript .claude/skills/scan-inbox/scripts/scan_inbox.scpt 48 false
Phase 2: Intelligence Extraction & Categorization
Analyze each email and categorize based on the following priority matrix:
🔴 CRITICAL - Job Opportunities (Priority Score: 100)
Detection Keywords:
- Role indicators: "interview", "position", "role", "opportunity", "career", "hiring", "application", "candidate"
- Seniority levels: "Principal", "Senior", "Staff", "Lead", "Architect"
- Engineering roles: "Engineer", "Developer", "Architect", "Technical Lead"
Extraction Requirements:
- Company name (from sender domain or subject)
- Role title (exact phrase)
- Sender name and email address
- Action required (interview, application, response)
- Received timestamp
Exclusions:
- Generic job board digests (Torre bulk emails, LinkedIn daily digests)
- "Apply now" promotional emails without specific role
- Job alerts with dozens of listings (bulk newsletters)
Professional Context Filters:
- Prioritize: Python, Backend, Cloud, AI/ML, Distributed Systems
- Seniority match: Principal, Senior, Staff levels
- Work style: Remote-first or hybrid opportunities
- De-prioritize: Junior, Entry-level, Intern positions
🔴 URGENT - Time-Sensitive Items (Priority Score: 90)
Detection Keywords:
- Urgency: "urgent", "ASAP", "immediate", "critical", "important"
- Deadlines: "expires", "deadline", "due by", "expires in [N] days", "by [date]"
- Action required: "action required", "please respond", "needs approval", "approval needed"
Extraction Requirements:
- What's due or expiring
- Deadline date/time (if present)
- Who requested it
- Consequences of missing deadline
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 · 252 lines · 0 tokens per session scan A 173763993254
inbox is a command published in the GitHub repository ronnycoding/my-personal-assistant (12 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,764 tokens. 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 2026-09-02.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
autobot-result
Print the most recent result.md for an autobot session, so the user can see how a bot is doing without attaching to its tmux session.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.