checkpoint

A session command that saves a timestamped copy of the current daily conversation transcript and adds a checkpoint note to it.

In plain words
What is it for?
Use it to archive the full conversation, record what has been completed, and add a note or summary to the session log.
Why use it?
It preserves your progress at a known point, so a long or interrupted session is easier to review or continue.

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/checkpoint
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 1,402 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 $0.01402
Opus 5 $0.00000 $0.00701
Sonnet 5 $0.00000 $0.00280
Haiku 4.5 $0.00000 $0.00140

Measured 2d ago against content hash 88c9fdc7a95c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

checkpoint 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/checkpoint.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a timestamped checkpoint in the current daily session transcript.

Command Usage

  • /checkpoint - Create checkpoint with auto-generated summary
  • /checkpoint [note] - Create checkpoint with specific note/context

What This Command Does

  1. Identify the current transcript file:

    • Look for ai-chats/transcripts/YYYY-MM-DD/daily-session-YYYY-MM-DD.md in the current vault
    • Use today's date
  2. Archive the current conversation:

    • Create archive directory: ai-chats/transcripts/YYYY-MM-DD/archives/
    • Export full transcript to Markdown: session-YYYY-MM-DD-HHMM-full.md
    • This preserves the full conversation at checkpoint time
  3. Generate checkpoint entry:

    • Current timestamp (e.g., ### ~3:45pm - Checkpoint)
    • Link to the archived full transcript
    • If user provided a note, use that as the summary line
    • Otherwise, generate a brief summary of what's been accomplished
    • Include structured data matching PreCompact format
  4. Append to transcript:

    • Add the checkpoint entry to the "Session Log" section (before "## Session Handoff")
    • Include key activities with [[wiki-links]]
    • Include summary points
  5. Update daily note:

    • Find today's daily note at journals/YYYY-MM-DD.md
    • Increment the checkpoint count (e.g., *(2 checkpoints)**(3 checkpoints)*)
    • Add a nested bullet with deep link to the checkpoint section

Checkpoint Entry Format (Transcript)

### ~[TIME] - Checkpoint
[Summary line - user note or auto-generated]. [[ai-chats/transcripts/YYYY-MM-DD/archives/session-YYYY-MM-DD-HHMM-full|Full transcript]]

**Session:** [[Session Type]] | [N] messages | [N] tool calls | [N] created | [N] modified

**Key Activities:**
- Created: `path/to/file` ([[Language]])
- Modified: `path/to/file` ([[Language]])
- [Other notable activities with wiki-links]

**Summary:**
- Key accomplishment 1 with [[wiki-links]]
- Key accomplishment 2
- Decisions or insights

---

Daily Note Entry Format

Read the full file on GitHub · 149 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 · 149 lines · 0 tokens per session scan A 88c9fdc7a95c

Subscribe to this mod's changes

checkpoint 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 1,402 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.