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 LandonSchropp/agent-toolkit --skill git-atomic-commitgit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/git-atomic-commit)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/git-atomic-commit"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/git-atomic-commit/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/landonschropp/agent-toolkit/git-atomic-commit"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/git-atomic-commit.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 | $0.00880 |
| Opus 5.5 | $0.00020 | $0.00352 |
| Sonnet 5.5 | $0.00010 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
git-atomic-commit 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Atomic Commit
An atomic commit captures one logical change. Each commit stays portable: it can be reviewed, reverted, cherry-picked, lifted into its own PR, edited, or reordered without rebase conflicts cascading through the work that came after.
Atomic commits also keep history honest. Without that discipline, the log records false starts and reversals — code added in one commit and removed in another — and readers have to trace every commit to know the final state.
Crucially, atomic commits optimize for reviewability. A commit should be small enough that a reviewer can understand all of it at once without context-switching. When a logical change grows too large for that, split it into smaller pieces that each still stand alone.
Why Changes in One File Get Split
A single file often picks up changes that belong in different commits:
- Refactor + behavior change: You restructured a function and then added new logic in the same edit. The refactor should land as its own commit ("make the change easy, then make the easy change") so reviewers can verify it's pure before evaluating the new behavior.
- Drive-by edits: Mid-feature you fixed a typo, removed dead code, or tidied imports. These don't belong with the feature work and shouldn't have to wait for it to merge.
- Independent concerns: A shared utility or config file gets touched by two unrelated efforts in the same session.
Don't let "but it's just one file" be the reason unrelated changes ship together. Optimize for the reviewer, not the commit count.
What Makes a Commit Reviewable
A reviewable commit:
- Stays focused: One purpose, one narrative. A reviewer should never ask "why is X in this commit?"
- Is small: Typically under 100–200 lines of changes. Larger changes force reviewers to split their attention and miss bugs.
- Stands alone: It can be understood without tracing through other commits. The diff should be self-explanatory.
When a commit strains these bounds, that's a signal to split it — into pieces that each still capture one logical change and pass this test on their own.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +1 lines · +6 tokens per session 859582b1199e
- 1mo ago First seen · 54 lines · 43 tokens per session scan A 40a99372f0e6
git-atomic-commit is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 880 once invoked, about $0.0002 per session on Opus 5.5. 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
loom-git-workflow
Git operations guidance including branching strategies, commit conventions, merge workflows, conflict resolution, and worktree management.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
commit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
conventional-commit
Generer conventional commit-meldinger med Nav-relevante scopes og breaking change-format.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.
configure-git-repository
Configure a Git repository with proper .gitignore, branch strategy, commit conventions, hooks, and remote setup. Covers initial setup and common patterns for R, Node.js, and Python projects. Use when initializing version control for a new project, adding a .gitignore for a specific language or framework, setting up…