checkpoint

A command for saving progress during a long development session without ending it.

In plain words
What is it for?
Use it after completing a discrete task, before switching work areas, when a session is getting long, or before a risky operation.
Why use it?
It preserves a recoverable work-in-progress record through a commit, optional verification tag, project-state update, and session note.

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/chrisdev1187/claude-code-forge/checkpoint
Clone the repo
git clone --depth 1 https://github.com/chrisdev1187/claude-code-forge

Made for: Claude Code.

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 223 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 $0.00223
Opus 5 $0.00000 $0.00112
Sonnet 5 $0.00000 $0.00045
Haiku 4.5 $0.00000 $0.00022

Measured yesterday against content hash 391fe8834e74, 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 yesterday.

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.

project-template/.claude/commands/checkpoint.md · 29 lines

What it actually says

/checkpoint — Mid-Session State Save

Run this during a long session to save progress without ending the session.

Steps

  1. Commit current work with rtk git commit -m "wip: [what you just finished]"
  2. Create a git tag if a component just passed its test loop:
    rtk git tag "verified-[component-name]"
    
  3. Update docs/MASTER_STATE.md — mark any newly verified components
  4. Write a one-line note in docs/SESSION_LOG.md under today's entry

When to run

  • After completing a discrete chunk of work (one agent template, one workflow, one config)
  • Before switching to a different part of the system
  • If the session is approaching 2+ hours (context accumulation risk)
  • Before any risky operation (git reset, file deletion, config change)

Quick version

rtk git add [specific files]
rtk git commit -m "wip: [brief description]"
# Then update MASTER_STATE.md manually
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. yesterday First seen · 29 lines · 0 tokens per session scan A 391fe8834e74

Subscribe to this mod's changes

checkpoint is a command published in the GitHub repository chrisdev1187/claude-code-forge (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 223 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.