checkpoint

checkpoint is a skill for Claude Code from hashgraph-online/hol-cigar. It costs 22 tokens per session (107 once invoked), scanned A, original, Apache-2.0.

A checkpoint procedure that records the current task state, decisions, active work, unresolved items, and supporting evidence. A checkpoint is a recoverable summary used when work is interrupted or context is shortened.

In plain words
What is it for?
Use it before context compaction, interruption, or a major task boundary to create an inspectable progress record.
Why use it?
It preserves the important state of a task so work can resume without reconstructing the entire conversation.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the cigar plugin — 5 skills, 3 agents, 18 hooks, 1 MCP server 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/hashgraph-online/hol-cigar/checkpoint
Any agent
npx skills add hashgraph-online/hol-cigar --skill checkpoint
Clone the repo
git clone --depth 1 https://github.com/hashgraph-online/hol-cigar

Made for: Claude Code.

Or install cigar, the plugin that ships this one along with the rest of its 5 skills, 3 agents, 18 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 checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/hashgraph-online/hol-cigar/checkpoint.svg)](https://agentmods.dev/skills/hashgraph-online/hol-cigar/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/hashgraph-online/hol-cigar/checkpoint"><img src="https://agentmods.dev/badge/skills/hashgraph-online/hol-cigar/checkpoint.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 107 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 $0.00022 $0.00107
Opus 5 $0.00011 $0.00053
Sonnet 5 $0.00004 $0.00021
Haiku 4.5 $0.00002 $0.00011

Measured 6d ago against content hash 76c8e815f6fe, 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.

adapters/claude-code/skills/checkpoint/SKILL.md · 10 lines

What it actually says

Use checkpoint_create to record the current task, decisions, active bundle, unresolved work, and present-state evidence. Keep the summary structured and concise. Return the checkpoint identifier, source snapshot, and expiry.

After compaction, compile current state from the checkpoint rather than reproducing an old transcript. Never read or attach a provider transcript as checkpoint data.

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 · 10 lines · 22 tokens per session scan A 76c8e815f6fe

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository hashgraph-online/hol-cigar (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 107 once invoked, about $0.0001 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.