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.
npx agentmods add skills/darkroomengineering/cc-settings/checkpointnpx skills add darkroomengineering/cc-settings --skill checkpointgit clone --depth 1 https://github.com/darkroomengineering/cc-settingsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.00968 |
| Opus 5 | $0.00030 | $0.00484 |
| Sonnet 5 | $0.00012 | $0.00194 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
checkpoint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint: Save & Restore Task State
Product-aware runner
Set these once for the active host. checkpoint.ts uses claudePath, so pass
the matching state root on every invocation.
# Standalone Codex
CHECKPOINT_RUNNER="${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.
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.
- 2d ago First seen · 124 lines · 60 tokens per session scan A 96bdb27136a6
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.
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.
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…
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…
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.
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.
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…