daily-session

An Obsidian command for starting a daily thinking or brainstorming session. Obsidian is a note-taking app; the command can read daily notes and previous handoffs, and in full mode creates a transcript and updates the daily note.

In plain words
What is it for?
Use it for morning planning, focused work sessions, quick context checks, or preparing notes for an end-of-day handoff.
Why use it?
It gathers relevant notes and preserves a record of the session, while light mode avoids creating extra files for quick check-ins.

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/daily-session
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 1,521 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 $0.01521
Opus 5 $0.00000 $0.00760
Sonnet 5 $0.00000 $0.00304
Haiku 4.5 $0.00000 $0.00152

Measured 2d ago against content hash bde666de4089, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

daily-session 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/daily-session.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start a daily thinking/brainstorm session in the Obsidian vault.

Usage

/daily-session          # Full mode (default) - creates transcript, updates daily note
/daily-session --light  # Light mode - context only, no file creation

Modes

Default (Full Mode)

Creates a transcript file, adds entry to daily note, full archival workflow. Use this for:

  • Morning session starts
  • Days with planned focused work
  • When you want full documentation

Light Mode (--light)

Reads context but skips file creation. Use this for:

  • Late starts (afternoon/evening)
  • Low-energy days
  • Quick check-ins
  • When you'll run /end-day shortly after

Light mode still:

  • Reads today's daily note
  • Finds and reads previous handoff
  • Scans recent exports
  • Greets with full context

Light mode skips:

  • Creating transcript file
  • Adding session entry to daily note

What This Command Does (Full Mode)

  1. Read today's daily note (journals/YYYY-MM-DD.md):

    • Extract mood from "Mood Check"
    • Extract focus items from "Today's Focus"
    • Note key reflections or context from their writing
    • Note any existing Claude Sessions entries
  2. Find and read the most recent handoff (handles gaps gracefully):

    • Search for transcripts: ai-chats/transcripts/*/daily-session-*.md
    • Sort by date descending, exclude today
    • Read the most recent one's "Session Handoff" section
    • Note how many days ago the last session was (for context)
    • If no previous transcript exists: proceed without handoff context
    • If handoff section is incomplete: use what's available, note the gap
  3. Scan recent Claude Code exports (cross-session context):

    • Search for summary files: ai-chats/claude-code/**/*-summary.md
    • Exclude: ai-chats/claude-code/seeds/ (daily session exports are redundant with handoff)
    • Filter to files modified since the last daily session date
    • For each summary found:
      • Parse YAML frontmatter (project, tags, duration, files_touched)
      • Extract Overview section (1-2 sentence summary)
      • Extract Next Steps / Open items
    • Group summaries by project for the transcript
    • If no exports found: note this but proceed (not all work generates exports)

Read the full file on GitHub · 212 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 · 212 lines · 0 tokens per session scan A bde666de4089

Subscribe to this mod's changes

daily-session 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 1,521 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.