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/tottinge/otter-skills/atomic-commitnpx skills add tottinge/otter-skills --skill atomic-commitgit clone --depth 1 https://github.com/tottinge/otter-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/tottinge/otter-skills/atomic-commit)<a href="https://agentmods.dev/skills/tottinge/otter-skills/atomic-commit"><img src="https://agentmods.dev/badge/skills/tottinge/otter-skills/atomic-commit.svg" alt="Measured on agentmods" 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 | $0.00102 | $0.01547 |
| Opus 5 | $0.00051 | $0.00773 |
| Sonnet 5 | $0.00020 | $0.00309 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atomic Commit
Preserve historical truth: every commit must be a complete repository state that actually existed on disk, was tested in exactly that form, and was vetted by a human. A stranger must be able to check out any commit and encounter a coherent change with green tests.
Atomicity begins when choosing the work, not when staging it. A small-looking commit assembled afterward from selected hunks is not atomic.
Non-negotiable invariants
- Green before every commit is absolute. Never create a failing, WIP, checkpoint, or “fixed by the next commit” commit.
- Incremental refactoring, tests, prescribed scans, and documentation are pre-commit work. Complete and verify them before presenting the feature commit for review.
- Commit the entire working-directory state. Never use partial staging, path-limited staging,
git add -p, or temporary reversal to manufacture commit boundaries. - Run all Git and verification commands from the repository root. Establish it with
git rev-parse --show-toplevel; do not assume the current directory is the root. - Every untracked file receives an explicit disposition: add, ignore, or delete. Make evident decisions autonomously; ask the human only when the correct disposition is uncertain.
- A human reviews the complete proposed commit after verification and before
git commit. - Human review is part of the rapid local microcommit loop, not a reason to enlarge batches or postpone a completed green step. Many human-reviewed commits in a day are entirely consistent with this skill.
- Use a Conventional Commits message that truthfully describes the whole state.
Choose the batch before editing
Begin from a clean, green repository. If it is dirty, do not add another intention. Finish and commit the existing state through this protocol, or ask the human how to resolve it.
Choose one meaningful, bounded change and state its intention. Then perform only that batch. Keep the batch small enough to understand, test, and review as a whole.
What ships with it
1 file 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.
- 3d ago First seen · 84 lines · 102 tokens per session scan A 8989c4850645
atomic-commit is a skill published in the GitHub repository tottinge/otter-skills (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,547 once invoked, about $0.0005 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
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…
commit
Git commit workflow with precommit hook handling, lint/type checking, README updates, and API reference updates. Use when the user wants to commit changes. Handles precommit hooks that modify files (formatting, linting) by re-staging and retrying. Runs ruff lint and pyright type checks on staged Python files, and…
git-commit
Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…
commit
Create a signed git commit following Conventional Commits, after running /pre-commit and /changelog when appropriate.
commit
Read this skill before making git commits.
et-git
ET git workflow for preparing commits and reviewing changes. Use when checking git status or diff, filtering unrelated files, staging task-scoped changes, writing Chinese commit messages, or synchronizing with remotes using rebase instead of merge.