By AfterRealm
Make Claude Code time-aware with peak hour warnings, session tracking, rate limit forecasts, and focus timers. Queued intents are automatically picked up and processed via Python scripts at session start and before each prompt.
Analyze your work patterns over time — when you typically work, peak vs off-peak usage, night owl detection. Use when asking about work habits, schedule patterns, optimal work times, "am I a night owl", "when do I actually work", weekday vs weekend ratios, or questions about self-observation of work rhythm.
Estimate the token cost of reading a file or directory before doing it. Use when asking "how many tokens would this cost", "how big is this file in tokens", "is this file too big to read", before reading large files, or when weighing whether to read something with limited context budget remaining.
Get a morning briefing with peak hour status, schedule outlook, and work recommendations for the day. Use at the start of a new day, when asking for a daily summary, "what should I work on today", "plan my day", "morning check-in", or when the user wants a quick orientation before settling into work.
Start a focus timer for deep work sessions. Tracks elapsed time and optionally reminds about breaks. Use when the user wants to focus, start a timer, or do a pomodoro session.
Check real rate limit usage from the Anthropic API — session (5-hour), weekly, and Opus utilization. Use when asking about rate limits, pacing, token usage, "how much runway do I have", "should I keep working", "am I burning too fast", "will I hit my limit", or wanting a forecast of remaining subscription budget.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code doesn't know what time it is. Father Time fixes that.
A plugin that gives Claude persistent time awareness — peak hour warnings, session tracking, rate limit forecasting, activity pattern learning, focus timers, and daily briefings. Built for the post-throttle era.
On March 26, 2026, Anthropic announced adjusted session limits during peak hours. Your 5-hour session limits now drain faster on weekdays between 5am-11am PT. Father Time helps you work around that.
But it's more than peak hours. Claude has no concept of time between prompts. It doesn't know if you've been working for 10 minutes or 10 hours. It doesn't know if it's Monday morning or Saturday midnight. Father Time gives it that context on every single prompt.
Every prompt is automatically injected with:
A time-aware assistant that can answer questions about scheduling, pacing, and work patterns.
| Skill | What It Does |
|---|---|
/father-time:time-menu | Interactive menu — pick from all capabilities below via a guided selector. |
/father-time:peak-hours | Am I in Anthropic's throttle window? Full timezone table included. |
/father-time:session-timer | How long has this session been running? Checkpoint suggestions at milestones. |
/father-time:daily-brief | Morning briefing — peak status, schedule outlook, activity insights, work recommendations. |
/father-time:pace-check | Rate limit forecasting. Estimates runway based on session duration and work intensity. |
/father-time:focus-mode | Focus timer with presets (pomodoro 25m, deep-work 90m, sprint 45m, marathon 3h). Non-intrusive. |
/father-time:activity-patterns | Analyze your work patterns over time. Night owl? Early bird? How much do you overlap with peak hours? |
/father-time:session-health | Session JSONL size, context window usage estimate, compaction proximity, and rate limit status. |
/father-time:context-budget | Estimate the token cost of reading a file or directory before doing it. Includes per-model cost comparison (Opus 4.7 / 4.6 / Sonnet 4.6 / Haiku 4.5), Opus 4.7 tokenizer headroom, and 1M-context notes. |
Anthropic's throttle window: Weekdays 5:00 AM – 11:00 AM Pacific Time
| Timezone | Peak Window |
|---|---|
| PT (Pacific) | 5:00 AM – 11:00 AM |
| MT (Mountain) | 6:00 AM – 12:00 PM |
| CT (Central) | 7:00 AM – 1:00 PM |
| ET (Eastern) | 8:00 AM – 2:00 PM |
| GMT/UTC | 1:00 PM – 7:00 PM |
| CET (Central Europe) | 2:00 PM – 8:00 PM |
| IST (India) | 6:30 PM – 12:30 AM |
| JST (Japan) | 10:00 PM – 4:00 AM |
| AEST (Australia East) | 11:00 PM – 5:00 AM |
| NZST (New Zealand) | 1:00 AM – 7:00 AM |
Add the AfterRealm marketplace and install:
claude plugin marketplace add AfterRealm/marketplace
claude plugin install father-time@afterrealm
Then restart Claude Code. All skills will be available globally.
Also available: Blunt Cake — brutal, funny code reviewer with 7 modes and 6 personalities. Both plugins live in the AfterRealm marketplace.
Father Time is nearly free to run.
| Component | Token Cost | When |
|---|---|---|
| Time injection hook | ~40 tokens/prompt | Every prompt (passive) |
| Skills | 300-800 tokens | Only when you invoke them |
| Agent | ~1,500 tokens | Only when spawned |
| Python scripts | 0 tokens | Run locally, no API calls |
Passive cost: ~40 tokens per prompt for the time/peak/session string. Over a 100-prompt session, that's ~4,000 tokens — 0.4% of a 1M context window. Essentially invisible.
Skills and the agent only consume tokens when you explicitly call them. The hook scripts run as local Python processes with zero API cost.
All data stays local. Activity patterns are stored in ${CLAUDE_PLUGIN_DATA} on your machine. Nothing is transmitted anywhere.
MIT
npx claudepluginhub afterrealm/father-time --plugin father-timeMultilingual voice input for anywhere you type into Claude — the Desktop App, Claude Code Desktop, or a regular Claude Code terminal. Hold a hotkey, speak any of 99 Whisper-supported languages, and the transcript pastes into whatever Claude window has focus. Fills the gap while official voice mode is English-only. Lightweight plugin — no MCP, no TTS, just a venv + Python script. (Windows-tested; macOS/Linux feedback welcome.)
Brutal but brilliant code reviewer with the personality of a celebrity chef. Real findings, real fixes, real jokes. 8 modes (standard, panel, diff, eval, skill review, batter battle, roast-a-thon, challenge) + 6 personalities + custom personality creator. Auto-fix and shareable roast cards built in.
UE5 Blueprint analysis, debugging, and teaching tools. Export Blueprints from a running UE5 editor, detect anti-patterns, and get beginner-friendly fix instructions.
Professional web accessibility auditor. Scans HTML, JSX, TSX, Vue, and Svelte for WCAG 2.2 Level AA violations, explains each finding in plain English, identifies who is affected, and provides concrete fixes. Four modes: full-audit, component-check, standards-check, compliance-report.
Time-aware agent for Claude Code. Peak hour warnings, session tracking, daily briefings, rate limit forecasting, focus timers, and activity pattern learning. Because Claude should know what time it is.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
AI-powered development tools for code review, research, design, and workflow automation.