checkpoint

checkpoint is a command for coding agents from hgahlot/claude-flow. It costs 0 tokens per session (312 once invoked), scanned A, original, MIT.

A command that saves the current work state to a file named STATE.md. The file records completed work, the task in progress, upcoming tasks, blockers, decisions, and recent activity.

In plain words
What is it for?
Use it before ending a session, when handing work to another session, or whenever you need a written checkpoint of the project plan and its status.
Why use it?
It prevents important context from being lost between sessions. A later session can use the file to understand where work stopped and what should happen next.

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/hgahlot/claude-flow/checkpoint
Clone the repo
git clone --depth 1 https://github.com/hgahlot/claude-flow

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/commands/hgahlot/claude-flow/checkpoint.svg)](https://agentmods.dev/commands/hgahlot/claude-flow/checkpoint)
Your own site
<a href="https://agentmods.dev/commands/hgahlot/claude-flow/checkpoint"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/checkpoint.svg" alt="Measured on agentmods" height="20"></a>
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 312 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 $0.00312
Opus 5 $0.00000 $0.00156
Sonnet 5 $0.00000 $0.00062
Haiku 4.5 $0.00000 $0.00031

Measured 5d ago against content hash d76b5f23887d, 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 5d 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 · 49 lines

What it actually says

/checkpoint — Save Current State to STATE.md

Capture a snapshot of the current session state for continuity across sessions.

Instructions

  1. Identify completed work — list tasks finished since last checkpoint
  2. Identify current position — what task is in progress right now
  3. Identify next tasks — what comes next in the plan
  4. Note any blockers — unresolved issues, open questions, external dependencies
  5. Write to STATE.md — overwrite with updated content

STATE.md Format

# Session State

## Last Session
Ended: <ISO timestamp>

## Last Completed Task
<Task ID and description from the plan>
Evidence: <brief description of verification performed>

## Current Task (In Progress)
<Task ID and description, or "none">

## Next Tasks Queue
1. <Task ID>: <description>
2. <Task ID>: <description>
3. <Task ID>: <description>

## Blockers
- <blocker description> — waiting on: <what/who>

## Recent Decisions
- <decision made and why — only non-obvious decisions>

## Activity Log
- [timestamp] <significant action taken>

Rules

  • Keep STATE.md under 200 lines
  • When it approaches 200 lines, summarize completed milestones into ROADMAP.md
  • Always include evidence for the last completed task
  • Blockers must name what is blocking, not just "blocked"
  • After writing STATE.md, confirm: "Checkpoint saved."
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. 5d ago First seen · 49 lines · 0 tokens per session scan A d76b5f23887d

Subscribe to this mod's changes

checkpoint is a command published in the GitHub repository hgahlot/claude-flow (53 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 312 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.