end-day

A session command that closes a daily conversation log and prepares a handoff, meaning a summary of work and next steps for the following day.

In plain words
What is it for?
Use it to find the correct unfinished daily transcript, summarize completed work, and record what should happen next.
Why use it?
It reduces the chance of losing context when a session ends late or continues after midnight.

Command

Install

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.

agentmods
npx agentmods add commands/jonathanprozzi/claude-utils/end-day
Clone the repo
git clone --depth 1 https://github.com/jonathanprozzi/claude-utils
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01045
Opus 5 $0.00000 $0.00522
Sonnet 5 $0.00000 $0.00209
Haiku 4.5 $0.00000 $0.00104

Measured 2d ago against content hash e8baa6dfd093, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

end-day 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 2d 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.

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.

commands/end-day.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrap up the daily session and generate handoff for tomorrow.

Usage

/end-day              # Auto-detect session date from most recent incomplete transcript
/end-day --date 2025-12-16   # Explicitly specify the session date

Date Detection (handles late-night sessions)

When running /end-day after midnight, the system date is technically "tomorrow" but you're conceptually wrapping up "yesterday." This command handles this automatically:

  1. If --date YYYY-MM-DD is provided: Use that date explicitly
  2. Otherwise, auto-detect:
    • Search for recent daily session transcripts: ai-chats/transcripts/*/daily-session-*.md
    • Find transcripts with an incomplete handoff (contains placeholder text: *To be generated at end of session)
    • Use the most recent incomplete transcript's date
    • If no incomplete transcript found, fall back to today's system date

This means running /end-day at 1am on 12/17 will correctly find and complete the 12/16 transcript if it's still open.

What This Command Does

  1. Determine session date (via auto-detection or --date flag)

  2. Read the session's transcript (ai-chats/transcripts/YYYY-MM-DD/daily-session-YYYY-MM-DD.md):

    • Review the Session Log entries and checkpoints
    • Identify key accomplishments, decisions, and open threads
  3. Scan the session date's Claude Code exports (cross-session aggregation):

    • Search for summary files: ai-chats/claude-code/**/*-summary.md
    • Filter to files with the session date in the filename (YYYY-MM-DD pattern)
    • For each summary found:
      • Parse YAML frontmatter (project, duration, files_touched)
      • Extract key accomplishments from Overview
      • Extract Next Steps / Open items
    • Group by project for the handoff
  4. Update the Session Handoff section in the transcript:

    • Summarize what was accomplished (this session)
    • Include "Other Sessions Today" table with cross-session work
    • Create "Unified Open Threads" merging all session next steps
    • Note key files touched or created
    • Add context for tomorrow's session

Read the full file on GitHub · 118 lines

Changes

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.

  1. 2d ago First seen · 118 lines · 0 tokens per session scan A e8baa6dfd093

Subscribe to this mod's changes

end-day is a command published in the GitHub repository jonathanprozzi/claude-utils (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,045 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 2026-08-30.