checkpoint

checkpoint is a skill for Claude Code from EternallLight/tgc-skills. It costs 49 tokens per session (571 once invoked), scanned A, original, MIT.

A workflow for saving current code changes as one Git commit and sending that commit to the remote repository while work continues.

In plain words
What is it for?
Use it when you want to check the current changes, run quick relevant checks, commit the intended files, and push them to a branch.
Why use it?
It creates a recoverable checkpoint during a longer task without ending the task or splitting the work into multiple commits.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md.

Part of the tgc-skills plugin — 9 skills shipped together

Good fit Use it when you want to check the current changes, run quick relevant checks, commit the intended files, and push them to a branch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eternalllight/tgc-skills/checkpoint
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.

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

Made for: Claude Code.

Or install tgc-skills, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/eternalllight/tgc-skills/checkpoint/github.svg)](https://agentmods.dev/skills/eternalllight/tgc-skills/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/checkpoint"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/checkpoint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for checkpoint

Your own site · 80×15
<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/checkpoint"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00571
Opus 5 $0.00024 $0.00285
Sonnet 5 $0.00010 $0.00114
Haiku 4.5 $0.00005 $0.00057

Measured 10d ago against content hash d977908a711f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checkpoint

Save the working tree as ONE commit and push it, then keep going. A checkpoint is a quick save, not commit surgery — no splitting, no interactive staging, no questions about which files to include.

Recipe

  1. See the change. Run git status --short, git diff, and git diff --cached. Resolve the default branch with gh repo view --json defaultBranchRef; if currently on it, create a feature branch first. Stop if the tree or index contains unrelated or sensitive files.
  2. Cheap verify. Run the repo's fastest relevant checks on the changed code — typecheck and lint from package.json scripts, Makefile, or CLAUDE.md; not the full test suite. If a check fails on something you changed, fix it or report the failure instead of committing — "only if green" is the contract even when unspoken.
  3. Stage by explicit path — the intended current work, never git add -A. Then inspect git diff --cached --name-only and git diff --cached; the index must contain only intended files. Treat plans and documentation like any other repo file.
  4. Commit using the repo's documented or recent-log convention. Fall back to a conventional message when the repo has no established convention.
  5. Push the current branch: git push, or git push -u origin <branch> the first time. Never force-push.
  6. Chain the review if asked. When the request mentions review ("and review", "run the loop"), invoke tgc-skills:review-loop after the push; it reports its heartbeat path before dispatching. Otherwise stop after the checkpoint and mention /tgc-skills:review-loop as the next step.

Then report in one line: commit hash, branch, file count, which checks ran.

Common mistakes

Mistake Fix
Running the full test suite Checkpoint = cheapest checks that cover the changed code
Committing when a check you touched is red Fix it or report; never checkpoint red code silently
Silently including an ambiguous file Stop when status contains unrelated or sensitive work
git add -A sweeping in unrelated files Stage intended files by explicit path

Read the full file on GitHub · 45 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. 10d ago First seen · 45 lines · 49 tokens per session scan A d977908a711f

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository EternallLight/tgc-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 571 once invoked, about $0.0002 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 2026-08-31.