checkpoint

checkpoint is a skill for Claude Code from toBzh30/Claude-Project-Bootstrap. It costs 50 tokens per session (384 once invoked), scanned A, original, MIT.

A session handover document that records project progress, current changes, test status, pending work, and environment details for later continuation.

In plain words
What is it for?
Use it when ending a session or preparing for a context reset to save a concise summary and provide a path for the next session to follow.
Why use it?
It preserves the context needed to resume work after the conversation is cleared or interrupted.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Part of the engineering-craft plugin — 9 skills shipped together

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 skills/tobzh30/claude-project-bootstrap/checkpoint
Any agent
npx skills add toBzh30/Claude-Project-Bootstrap --skill checkpoint
Clone the repo
git clone --depth 1 https://github.com/toBzh30/Claude-Project-Bootstrap

Made for: Claude Code.

Or install engineering-craft, the plugin that ships this one along with the rest of its 9 skills.

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 checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/tobzh30/claude-project-bootstrap/checkpoint.svg)](https://agentmods.dev/skills/tobzh30/claude-project-bootstrap/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/tobzh30/claude-project-bootstrap/checkpoint"><img src="https://agentmods.dev/badge/skills/tobzh30/claude-project-bootstrap/checkpoint.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 384 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 5.1 $0.00050 $0.00384
Opus 5 $0.00025 $0.00192
Sonnet 5 $0.00010 $0.00077
Haiku 4.5 $0.00005 $0.00038

Measured 6d ago against content hash f122d933eb5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

plugins/engineering-craft/skills/checkpoint/SKILL.md · 30 lines

What it actually says

Capture the current session as a resumable handover so a fresh session (after /clear) can pick up cold without undoing work.

Steps

  1. Run printf '%s-%s' "$(date +%Y-%m-%dT%H%M)" "$(openssl rand -hex 3)" to get a timestamp with a random suffix (e.g. 2026-04-22T1717-a3f9c1) for the filename.

  2. Generate a summary covering these sections — keep the whole document under 400 words:

    • Project: name, repo path, one-line description
    • Accomplished: bullet list of what was done this session
    • Current state: branch, uncommitted changes, open PRs, test status, anything a fresh session needs to know to not undo work
    • Pending: numbered list of next actions with enough detail to resume cold (include specific commands, file paths, URLs where relevant)
    • Environment: non-obvious setup that won't survive a shell restart (e.g. ssh-add, nvm, auth tokens, background processes)
  3. Write the summary to ~/.claude/handovers/<timestamp>.md.

  4. Print exactly this (substituting the real timestamp):

Saved to ~/.claude/handovers/<timestamp>.md

After /clear, paste this to resume:
  Read ~/.claude/handovers/<timestamp>.md and resume from where we left off
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. 6d ago First seen · 30 lines · 50 tokens per session scan A f122d933eb5e

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository toBzh30/Claude-Project-Bootstrap (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 384 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.

Related

Other skills, from other repositories