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/jm-paunlagui/catherine/commit-lognpx skills add Jm-Paunlagui/CATHERINE --skill commit-loggit clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINEWhat 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 | $0.00099 | $0.01133 |
| Opus 5 | $0.00049 | $0.00566 |
| Sonnet 5 | $0.00020 | $0.00227 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
commit-log 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a release-note generator for the Aumovio platform. Every invocation produces two outputs in order — commit message(s) first, changelog entry second. Apply caveman-commit rules throughout. No fluff. Why over what.
Step 1 — Commit message(s)
Apply these rules (inherited from caveman-commit):
- Format:
<type>(<scope>): <imperative summary> - Types:
featfixrefactorperfdocstestchorebuildcistylerevert - Subject ≤50 chars preferred, hard cap 72. No trailing period.
- Body only when the WHY is non-obvious, breaking, or migration-relevant.
- Wrap body at 72 chars. Bullets
-not*. - Never: "this commit", "I", "we", AI attribution, emoji, restate file name.
Always produce two separate commit blocks — one for Frontend, one for Backend. Label each block clearly:
### Frontend
<commit message here>
### Backend
<commit message here>
If one side has no changes this session, output a _No changes._ line under that
heading instead of omitting the block. Never silently drop a section — both headings
must always appear so the output is consistent and copy-paste ready.
Step 2 — Changelog entry fields
Produce a fenced block with exactly these fields — ready to paste into the Version History "New Entry" modal:
Type: <feat | fix | perf | refactor | security | docs | chore>
Title: <≤60 chars, title case, no version number>
Message: <1–2 sentences, present tense, user-facing benefit first>
What Changed:
- <top-level change>
- <nested sub-detail if needed>
- <top-level change>
...
Rules for changelog fields:
- Type must match the commit type exactly.
- Title is the human-readable feature name — not the commit subject.
- Message is what a non-engineer reading the changelog will understand. Lead with the user-visible benefit, not the implementation detail.
- What Changed mirrors the commit body bullets but written for an audience that includes non-engineers. Max 8 top-level bullets. Nest sub-bullets with 2-space indent (matches the changelog textarea parser).
- Always produce one combined changelog entry covering both Frontend and Backend changes together. Users read the changelog as a product release, not a per-repo diff — merge the What Changed bullets from both sides into a single list, grouping FE and BE items under sub-headings only when the lists are long enough to warrant separation (6+ bullets per side). When one side has no changes, simply omit that side's bullets — do not add a "No changes" line.
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 · 138 lines · 99 tokens per session scan A dc93bba42639
commit-log is a skill published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,133 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
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
ship
Build, commit, push & version bump workflow - automates the complete release cycle.
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
release
Create a new es-toolkit release (version bump, changelog, tag).
git-workflow
安全处理 Git 状态检查、提交信息、commit、分支、push、PR 和 rebase。用于用户要求检查改动、生成或创建提交、管理分支、推送、发起 PR 或整理历史时;严格区分每个动作的授权,并保护工作树中已有和无关的修改。.
zed-cherry-pick
Cherry-pick one or more merged PRs and/or commits into Zed's preview or stable release branch. Use this whenever the user mentions cherry-picking to preview/stable, a failed cherry-pick run, or wants to manually port fix(es) into a release branch.