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 netopsengineer/axiom --skill commit-messagegit clone --depth 1 https://github.com/netopsengineer/axiomWrote 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/netopsengineer/axiom/commit-message)<a href="https://agentmods.dev/skills/netopsengineer/axiom/commit-message"><img src="https://agentmods.dev/badge/skills/netopsengineer/axiom/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/skills/netopsengineer/axiom/commit-message"><img src="https://agentmods.dev/badge/skills/netopsengineer/axiom/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 | $0.00218 | $0.03250 |
| Opus 5.5 | $0.00087 | $0.01300 |
| Sonnet 5.5 | $0.00044 | $0.00650 |
| Haiku 4.5 | $0.00022 | $0.00325 |
Grade A, and why
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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message Generation
Read the staged diff, decide every field yourself using the rubrics below, and surface one assembled message for a single yes/no confirmation. Don't prompt field-by-field (a GUI extension can afford that; a chat turn can't), and don't short-circuit to a bare git commit -m "fix stuff" — if this skill loaded, run the full flow and never bypass hooks.
Repo defaults
Format: <type>(<scope>): <emoji> <subject>
Emoji style: Unicode glyph (e.g. 🐛 not :bug:)
Scope default: none (include only if the diff points clearly at one)
Co-Authored-By: off (this repo's history doesn't use the trailer)
Body default: skip unless the diff is non-trivial (>~10 lines, multi-file, or non-obvious why)
Footer default: skip; reserve for `BREAKING CHANGE:` or `Closes #N`
Subject limits: warn at >50 chars; hard cap at 72
Hooks: gitleaks runs pre-commit; do not bypass on failure
These are bootstrap defaults from this repo's history. In a different repo, re-detect during preflight (Phase 1 step 5) and adjust silently — observed in-repo history wins.
When to ask the user
Only stop and ask in these cases — otherwise decide and continue:
- Nothing staged. Offer to stage by filename (never
git add -A/-u/.). - On
master,main, or detached HEAD. Offer to create a new branch, move the staged changes there, then resume on that branch. Refuse to commit directly to master/main. - Suspicious staged content (
.env*,*.key,*.pem, files ≥1 MB, secrets in diff). Show the offending file/line, ask whether to unstage or proceed. - Genuinely ambiguous type or emoji choice — i.e., two options are equally defensible from the rubric and the choice changes how a reader will interpret the commit (e.g.,
featvsfixwhen the change adds a new code path that also corrects bad behavior). State the options and the tradeoff in one line, then wait. If the rubric picks a clear winner, do not ask. - Final assembled message. Always show the complete commit message in a fenced block and wait for explicit confirmation before running
git commit.
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 First seen · 220 lines · 218 tokens per session scan A 1846c5a4f893
commit-message is a skill published in the GitHub repository netopsengineer/axiom (5 stars, last pushed yesterday), licensed MIT. It adds 218 tokens to every session and 3,250 once invoked, about $0.0009 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
feature-flow
Complete git workflow orchestration (GitHub/GitLab/Forgejo) - branch, issue, commit.
commit
Create conventional commit from staged changes with approval.
jira-delivery
Close the needs-fix branch for both ticket classes: isolated git worktree, a red test BEFORE any implementation on change tickets, delegation to a core executor, every publish action (push / PR / comment / QA transition) gated behind a green @verification-agent verdict, commit + push + PR, then writeback via…
git-commit
Generate conventional commit messages when staging files for commit in any of the project's repos. Do not use for git tag messages, merge commit messages, changelog entries, or automated version bump commits.
pr-generator
Use this skill when creating a pull request — generate the title, structured description, and review checklist from the branch's actual commits and diff. Don't use it for commit messages (git-commit skill) or changelogs.
committing-staged-with-message
Generate commit message for staged changes, pause for approval, then commit. Stage files first with git add, then run this skill.