Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/stefaniuk/loadoutnpx agentmods add commands/stefaniuk/loadout/util.git-commit-messageWrote 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/commands/stefaniuk/loadout/util.git-commit-message)<a href="https://agentmods.dev/commands/stefaniuk/loadout/util.git-commit-message"><img src="https://agentmods.dev/badge/commands/stefaniuk/loadout/util.git-commit-message/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/commands/stefaniuk/loadout/util.git-commit-message"><img src="https://agentmods.dev/badge/commands/stefaniuk/loadout/util.git-commit-message.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 | $0.00011 | $0.02437 |
| Opus 5.5 | $0.00004 | $0.00975 |
| Sonnet 5.5 | $0.00002 | $0.00487 |
| Haiku 4.5 | $0.00001 | $0.00244 |
Grade A, and why
util.git-commit-message 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandatory preparation:
- The script in §A detects and fetches the repository's actual base branch (not assumed to be
main) locally if missing. This base branch is used only for branch-naming context and tone, never as commit evidence. - Read language/tooling instructions that apply to the files actually staged or modified in the working tree (for example python.instructions.md, typescript.instructions.md, makefile.instructions.md, etc.). Do not load instructions for files that are only in already-committed history - they are out of scope.
Goal 🎯
Produce three copy-ready outputs that describe the next commit the user is about to make:
- A Branch Name: if already on a feature branch, report whether it is suitable (and suggest an improvement if not); if on the detected base branch (see §A) or detached
HEAD, propose a new branch usingscope-short-description(e.g.auth-add-sso-callback). - A single-line conventional Commit Message (
type(scope): summary) describing the dominant change in the commit being prepared. - A commit body with an overview and highlights capturing intent and rationale (when evidenced), not just a restatement of file changes.
These outputs are the primary narrative source for pull-request descriptions: util.gh-pr-content.prompt.md reads git log <base>..HEAD (commit subjects + bodies) as its first evidence tier. Write every commit so it stands alone and aggregates cleanly with its siblings into a PR description; Step 3 maps each body part to the PR section it feeds.
Scope policy (non-negotiable) 🎯
The commit message describes the next commit, whose content is only the staged changes. This section describes evidence precedence only, it does not instruct you to run anything. The single sanctioned command runs once in §A; everything named below is a description of a block already present in the resulting report.
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 First seen · 142 lines · 11 tokens per session scan A e20774ec2ede
util.git-commit-message is a command published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 13d ago), licensed MIT. It adds 11 tokens to every session and 2,437 once invoked, about $0.0000 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 2026-09-12.
Other commands, from other repositories
sddp-implement
Command description: Implement the current feature tasks. Argument hint: [optional: phase or task to start from] Command category: feature-delivery Prerequisites: spec, plan, tasks, checklists:complete-if-present.
al-pr-prepare
Prepare a clean, documented pull request draft for AL features or fixes with summary, testing notes, and checklist. ALDC workflow (Copilot prompt al-pr-prepare); invoke explicitly.
speckit.companion.living-sync
Sync living specs from your current changes — group working-tree changes (uncommitted included) by capability and update every affected spec in one pass (opt-in, update-not-regenerate, never halts).
sddp-implement-qc-loop
Command description: Run implement and QC in a continuous loop. Argument hint: [optional: feature directory or branch name] Command category: orchestration Prerequisites: spec, plan, tasks.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
sddp-specify
Command description: Create a feature specification from a feature description. Argument hint: [feature description] Command category: feature-delivery Prerequisites: project-instructions.