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/jonathanprozzi/claude-utils/end-daygit clone --depth 1 https://github.com/jonathanprozzi/claude-utilsWhat 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 | $0.01045 |
| Opus 5 | $0.00000 | $0.00522 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00104 |
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.
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:
- If
--date YYYY-MM-DDis provided: Use that date explicitly - 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
- Search for recent daily session transcripts:
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
-
Determine session date (via auto-detection or
--dateflag) -
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
-
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
- Search for summary files:
-
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
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.
- 2d ago First seen · 118 lines · 0 tokens per session scan A e8baa6dfd093
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.