checkpoint

A project-state snapshot tool that saves git information, uncommitted changes, governance settings, and environment details in a JSON file. It can save, restore, list, and manage these checkpoints.

In plain words
What is it for?
Use it before experiments or risky changes, to list saved states, or to restore a checkpoint and receive the commands needed to return to it without automatically running destructive git operations.
Why use it?
It makes it easier to return to a known project state while keeping project-tracking context alongside the code state.

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/nxtg-ai/forge-plugin/checkpoint
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
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 1,204 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 $0.01204
Opus 5 $0.00000 $0.00602
Sonnet 5 $0.00000 $0.00241
Haiku 4.5 $0.00000 $0.00120

Measured 2d ago against content hash b00bf5f18aa8, 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.

docs/commands/checkpoint.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:checkpoint

Save, restore, list, and manage project state checkpoints for safe experimentation and rollback.

Level L1 Vibe Coder
Category State Management
Syntax `/forge:checkpoint [save

What It Does

/forge:checkpoint creates lightweight project state snapshots that capture your git commit, branch, uncommitted changes, governance state, and environment metadata in a single JSON file. Unlike git stash or branches, checkpoints are Forge-aware -- they save governance state alongside git state so you can restore not just your code position but your project tracking context.

Checkpoints are stored in .claude/checkpoints/ as individual JSON files. Each checkpoint records the git commit hash, branch name, porcelain status of uncommitted changes, the full governance.json contents, and environment details like Node version and working directory. Restoring a checkpoint shows you exactly what changed and provides the git commands to return to that state, but does not automatically run destructive git operations -- you stay in control.

Without checkpoints, rolling back means remembering commit hashes, manually restoring governance state, and hoping you can reconstruct the project context you had. Checkpoints make experimentation safe: save before a risky refactor, try it, and restore if it does not work out.

Syntax & Options

/forge:checkpoint [save|restore|list|clear] [checkpoint-name]
Option Description
save [name] Save current state. If no name provided, auto-generates cp-YYYYMMDD-HHMMSS. Default operation if no subcommand specified.
restore <name> Display checkpoint contents, show diff against current state, and offer to restore governance.
list Show all saved checkpoints with timestamps, branches, and commit hashes.
clear <name> Delete a specific checkpoint.

When to Use It

  • Before a major refactor: Save state so you can roll back if the refactoring breaks something.
  • Before experimental changes: Trying a new approach? Checkpoint first.
  • Before deployment: /forge:deploy creates automatic checkpoints, but you can also create named ones.
  • End of work session: Capture your exact state so the next session starts from a known point.

Read the full file on GitHub · 125 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 · 125 lines · 0 tokens per session scan A b00bf5f18aa8

Subscribe to this mod's changes

checkpoint is a command published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,204 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 2026-08-31.