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 skills add EternallLight/tgc-skills --skill checkpointgit clone --depth 1 https://github.com/EternallLight/tgc-skillsWrote 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.
[](https://agentmods.dev/skills/eternalllight/tgc-skills/checkpoint)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- See the change. Run
git status --short,git diff, andgit diff --cached. Resolve the default branch withgh repo view --json defaultBranchRef; if currently on it, create a feature branch first. Stop if the tree or index contains unrelated or sensitive files. - 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.
- Stage by explicit path — the intended current work, never
git add -A. Then inspectgit diff --cached --name-onlyandgit diff --cached; the index must contain only intended files. Treat plans and documentation like any other repo file. - Commit using the repo's documented or recent-log convention. Fall back to a conventional message when the repo has no established convention.
- Push the current branch:
git push, orgit push -u origin <branch>the first time. Never force-push. - Chain the review if asked. When the request mentions review ("and review", "run
the loop"), invoke
tgc-skills:review-loopafter the push; it reports its heartbeat path before dispatching. Otherwise stop after the checkpoint and mention/tgc-skills:review-loopas 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 |
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.
- 10d ago First seen · 45 lines · 49 tokens per session scan A d977908a711f
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.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.