checkpoint

A checkpoint tool for saving and restoring project state. A checkpoint records tracked files and uncommitted changes so they can later be reapplied during a rollback.

In plain words
What is it for?
Use it to save labeled checkpoints, list or inspect them, and restore a selected checkpoint when you need to undo a risky operation.
Why use it?
It provides a recovery point before risky refactors, migrations, or destructive edits. This makes it easier to return to a known state if the work goes wrong.

Skill for Claude CodeCodex

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/darkroomengineering/cc-settings/checkpoint
Any agent
npx skills add darkroomengineering/cc-settings --skill checkpoint
Clone the repo
git clone --depth 1 https://github.com/darkroomengineering/cc-settings

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 968 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 $0.00060 $0.00968
Opus 5 $0.00030 $0.00484
Sonnet 5 $0.00012 $0.00194
Haiku 4.5 $0.00006 $0.00097

Measured 2d ago against content hash 96bdb27136a6, 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.

skills/checkpoint/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checkpoint: Save & Restore Task State

Product-aware runner

Set these once for the active host. checkpoint.ts uses claudePath, so pass the matching state root on every invocation.

# Standalone Codex
CHECKPOINT_RUNNER="${CODEX_HOME:-$HOME/.codex}/darkroom/source/src/scripts/checkpoint.ts"
CC_STATE_ROOT="${CODEX_HOME:-$HOME/.codex}/darkroom/state"

# Claude Code instead uses:
# CHECKPOINT_RUNNER="$HOME/.claude/src/scripts/checkpoint.ts"
# CC_STATE_ROOT="$HOME/.claude"

Subcommands

save [label]

Save current state with an optional label.

CC_SETTINGS_HOME="$CC_STATE_ROOT" bun "$CHECKPOINT_RUNNER" save "Completed phase 3 migration"

list

List all checkpoints for the current project.

CC_SETTINGS_HOME="$CC_STATE_ROOT" bun "$CHECKPOINT_RUNNER" list

show [checkpoint-id]

Show details of a specific checkpoint.

CC_SETTINGS_HOME="$CC_STATE_ROOT" bun "$CHECKPOINT_RUNNER" show chk-20240115-103000

restore [checkpoint-id] [--force]

Real, opt-in rollback — restores tracked files (working tree + index) to exactly what they were at save time, then reapplies whatever uncommitted changes existed at that moment (captured as a patch when the checkpoint was saved). Untracked files are never touched or deleted; if any existed at save time they're just listed as a warning (their content was never captured). Scope note: restore reconstructs file content only — anything that was staged at save time comes back as unstaged working-tree changes (the patch reapplies to the worktree; index state is intentionally not reconstructed).

Safety rails:

  • Auto safety-checkpoint first. Before anything is touched, the current state is saved as its own checkpoint and its id is printed — restore is itself reversible by restoring that id (with --force).
  • Branch/sha guard. If the current branch or HEAD differs from what the checkpoint recorded, restore refuses and tells you to check out that branch or pass --force.
  • Legacy checkpoints (saved before this patch-capture feature existed) have no recorded diff to restore from. Restoring one prints "legacy checkpoint: metadata only, nothing restored" and falls back to the old print-only behavior — review the dumped JSON and continue manually.

Read the full file on GitHub · 124 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 · 124 lines · 60 tokens per session scan A 96bdb27136a6

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository darkroomengineering/cc-settings (42 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 968 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

astro-dso-doc

Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…

jjmartres/ai-coding-agents · 244 tokens

document-code

Apply Google Style documentation standards to Python, Go, TypeScript, and Terraform code. Use when writing or reviewing code that needs docstrings/comments/JSDoc, when asked to "document this code", "add docstrings", "follow Google Style", or when improving code documentation quality. Supports Python docstrings, Go…

jjmartres/ai-coding-agents · 88 tokens

work-on-ticket

Fetches Jira ticket details, creates an appropriately named branch, and initiates the task planning workflow. Use when the user says "work on [TICKETID]" or similar phrases.

jjmartres/ai-coding-agents · 41 tokens

datadog

Use this skill when you need to search Datadog logs, query metrics, tail logs in real-time, trace distributed requests, investigate errors, compare time periods, find log patterns, check service health, or export observability data.

jjmartres/ai-coding-agents · 51 tokens

document-project

Generate comprehensive, professional project documentation structures including README, ARCHITECTURE, USERGUIDE, DEVELOPERGUIDE, and CONTRIBUTING files. Use when the user requests project documentation creation, asks to "document a project", needs standard documentation files, or wants to set up docs for a new…

jjmartres/ai-coding-agents · 79 tokens