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/netopsengineer/axiom/commit-messagenpx skills add netopsengineer/axiom --skill commit-messagegit clone --depth 1 https://github.com/netopsengineer/axiomWhat 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 | $0.00218 | $0.03250 |
| Opus 5 | $0.00109 | $0.01625 |
| Sonnet 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 yesterday.
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.
- yesterday 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 6d ago), licensed MIT. It adds 218 tokens to every session and 3,250 once invoked, about $0.0011 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
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.