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 commands/orlando-japan/claude-code-setting/commit-smartgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWhat 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 | $0.00012 | $0.00367 |
| Opus 5 | $0.00006 | $0.00183 |
| Sonnet 5 | $0.00002 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
commit-smart 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.
What it actually says
Produce a commit from the current working state.
Step 1 — inspect:
- Run
git status(no-uall). - Run
git difffor unstaged andgit diff --stagedfor staged. - Run
git log -5 --onelineto match the repo's message style.
Step 2 — classify changes:
Group the diff into logical units. If the diff contains multiple logical changes, ask the user whether to split into multiple commits rather than bundling.
Step 3 — stage:
- Stage files by name, never
git add .orgit add -A. - Never stage
.env, credentials, lockfile-unrelated-to-dep-changes, or build artifacts. Warn if the user asks you to.
Step 4 — write the message:
Format:
<type>(<scope>): <subject>
<body: why, not what>
Types: feat, fix, refactor, test, docs, chore, perf, build, ci. Subject imperative, lowercase, no period, ≤72 chars.
Skip the body for obvious changes (typo, dep bump). Include it when the why isn't in the diff.
Step 5 — commit:
Pass the message via heredoc. Do not use --no-verify. If a hook fails, fix the underlying issue and create a new commit — don't amend.
Do not push.
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 · 42 lines · 12 tokens per session scan A 40935eb71d0d
commit-smart is a command published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 367 once invoked, about $0.0001 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 commands, from other repositories
speckit.git.commit
Auto-commit changes after a Spec Kit command completes.
commit
Smart commit that stages only conversation-relevant changes.
commit-all
Group all changes semantically and commit each group separately.
commit
Based on the above changes, create a single git commit.
commit
This command helps you create well-formatted commits with conventional commit messages and emoji.
commit
Safe git commit practices for MindRoom.