checkpoint

A command that writes a progress checkpoint describing the current coding session so work can continue after the conversation is restarted.

In plain words
What is it for?
Use it before a context reset or when handing ongoing work to a later session.
Why use it?
It preserves decisions, completed work, open tasks, important files, and blockers when the current context needs to be cleared.

Command for Claude Code

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/dgunning/edgartools/checkpoint
Clone the repo
git clone --depth 1 https://github.com/dgunning/edgartools

Made for: Claude Code.

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 763 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 $0.00006 $0.00763
Opus 5 $0.00003 $0.00381
Sonnet 5 $0.00001 $0.00153
Haiku 4.5 $0.00001 $0.00076

Measured 2d ago against content hash 2e88f48a33e7, 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/checkpoint.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Progress Checkpoint

You are creating a checkpoint of the current work session to enable a clean context restart.

Step 1: Determine Context

Ask yourself:

  • What is the main task we're working on?
  • What's a brief, descriptive name for this task? (e.g., "oauth-migration", "fix-bug-429", "add-13f-support")

Step 2: Create Checkpoint Document

Create a progress document with this structure:

Filename: docs-internal/sessions/session-{task-name}-{YYYY-MM-DD}.md

Use today's date and a brief task name (kebab-case, max 3-4 words).

Document Structure:

# Session Checkpoint: {Task Name}

**Date**: {YYYY-MM-DD}
**Time**: {HH:MM}
**Branch**: {current git branch}

## Task Summary
{1-2 sentence description of what we're working on}

## Completed ✅

- {Specific accomplishment with file path}
- {Another completed item}

## In Progress 🔄

- {Current work item}
- {Any blockers or issues encountered}

## Remaining Tasks ⬜

- [ ] {Next task to complete}
- [ ] {Another remaining task}

## Key Decisions 🎯

- **{Decision topic}**: {What was decided and why}
- **{Another decision}**: {Rationale}

## Important Files 📁

- `path/to/file.py` - {What this file does in this context}
- `path/to/another.py` - {Why this file matters}

## Next Steps 🚀

1. {Explicit next action}
2. {Second action}
3. {Third action}

## Context Notes

{Any important context that would be lost after /clear - patterns discovered,
gotchas encountered, areas of concern, etc.}

Step 3: Quality Check

Ensure the checkpoint includes:

  • ✅ Specific file paths (not vague "updated files")
  • ✅ Clear next steps (actionable, not vague)
  • ✅ Technical decisions with rationale
  • ✅ Any blockers or issues that need attention
  • ✅ Brief enough to scan quickly (<150 lines ideal)

Step 4: Save and Instruct

After creating the document, tell the user:

✅ Checkpoint saved to: {filename}

To continue after clearing context:
1. Type: /clear
2. Type: @{filename} /catchup
3. Say: "Continue with {specific next step from Next Steps}"

Alternative quick restart:
- /catchup (will catch git changes including this checkpoint if committed)

Ready to clear when you are.

Read the full file on GitHub · 121 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 · 121 lines · 6 tokens per session scan A 2e88f48a33e7

Subscribe to this mod's changes

checkpoint is a command published in the GitHub repository dgunning/edgartools (2,635 stars, last pushed yesterday), licensed MIT. It adds 6 tokens to every session and 763 once invoked, about $0.0000 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 2026-08-30.