zencheckpoint

zencheckpoint is a command for Claude Code from Fredje777/claude-zenvibe. It costs 67 tokens per session (885 once invoked), scanned A, original, MIT.

A session checkpoint command that saves coding progress without compressing the current conversation context.

In plain words
What is it for?
Use it to commit and push suitable changes, record work and decisions in docs/JOURNAL.md, and confirm that it is safe to compact the session.
Why use it?
It gives you a bookmark before manually using context compression, while leaving that compression decision to you.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the SlashCommand tool; mentions Claude Code.

Part of the zenvibe plugin — 3 commands, 2 hooks, 1 MCP server shipped together

Good fit Use it to commit and push suitable changes, record work and decisions in docs/JOURNAL.md, and confirm that it is safe to compact the session.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/fredje777/claude-zenvibe/zencheckpoint
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.

Clone the repo
git clone --depth 1 https://github.com/Fredje777/claude-zenvibe

Made for: Claude Code.

Or install zenvibe, the plugin that ships this one along with the rest of its 3 commands, 2 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for zencheckpoint

README.md
[![agentmods](https://agentmods.dev/badge/commands/fredje777/claude-zenvibe/zencheckpoint/github.svg)](https://agentmods.dev/commands/fredje777/claude-zenvibe/zencheckpoint)
Your own site
<a href="https://agentmods.dev/commands/fredje777/claude-zenvibe/zencheckpoint"><img src="https://agentmods.dev/badge/commands/fredje777/claude-zenvibe/zencheckpoint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for zencheckpoint

Your own site · 80×15
<a href="https://agentmods.dev/commands/fredje777/claude-zenvibe/zencheckpoint"><img src="https://agentmods.dev/badge/commands/fredje777/claude-zenvibe/zencheckpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 885 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00067 $0.00885
Opus 5 $0.00034 $0.00443
Sonnet 5 $0.00013 $0.00177
Haiku 4.5 $0.00007 $0.00089

Measured 12d ago against content hash efe428ad643a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zencheckpoint 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 12d 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/zencheckpoint.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user wants to save the current state without destroying context. You make a clean checkpoint, then confirm they can compact safely if they wish.

Output language: Default to English. If CLAUDE.md is in French OR the journal contains French entries, write your output in French. Otherwise English.

Important: you never run /compact yourself. Claude Code explicitly excludes /compact from the SlashCommand tool. Compaction stays an action the user triggers manually. Your role here is solely to secure context beforehand.

The PreCompact hook does the same work automatically if the user types /compact without running this skill first — so this skill is essentially an on-demand checkpoint, also useful mid-task to bookmark without compacting.

Workflow

0. Verify the working directory is a git repo

Run git rev-parse --is-inside-work-tree. If it fails, skip step 1 entirely, write only the journal entry, and mention "not a git repo" in the confirmation.

1. Commit + push committable changes

  • Run git status and git log -5 --oneline first.
  • Stage clean files. Skip half-written WIP (and warn the user — never commit broken code).
  • Commit with a meaningful message that summarizes the session, following the project's existing convention.
  • Push if a remote is configured.

2. Update the journal

Prepend a new entry at the top of docs/JOURNAL.md (or JOURNAL.md at root). Create docs/JOURNAL.md if neither exists.

This entry is session-focused, shorter than a full handoff:

## YYYY-MM-DD HH:MM — Checkpoint

### Done this session
- ...

### Technical decisions
- ...

### Files touched
- path/to/file
- ...

### Clear next step
- ... (one actionable line)

Keep it tight. The point is to bookmark the state, not write a sprint review.

3. Confirm

Output exactly this block, no more, no less:

✓ Checkpoint
✓ Commit: <sha> <message>   (or: "nothing to commit")
✓ Push: <branch> → <remote>   (or: "no remote")
✓ Journal: docs/JOURNAL.md

🧘 It's safe to compact now. Type /compact to proceed.

Read the full file on GitHub · 84 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. 12d ago First seen · 84 lines · 67 tokens per session scan A efe428ad643a

Subscribe to this mod's changes

zencheckpoint is a command published in the GitHub repository Fredje777/claude-zenvibe (2 stars, last pushed 18d ago), licensed MIT. It adds 67 tokens to every session and 885 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-31.