kavo: Skill for Claude Code

.claude/skills/conventions/SKILL.md

conventions is a skill for Claude Code from kavo-labs/kavo. It costs 38 tokens per session (598 once invoked), scanned A, original, MIT.

A shared naming scheme for issue labels, branch names, and commit message prefixes in a software repository.

In plain words
What is it for?
Use it when labeling issues, creating branches, or writing Conventional Commit messages for features, fixes, tests, documentation, and other changes.
Why use it?
It keeps related work consistently labeled across project tracking and Git, making changes easier to identify and organize.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is kavo-labs/kavo's own configuration. It tells Claude Code how to work on kavo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kavo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kavo-labs/kavo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kavo-labs/kavo/main/.claude/skills/conventions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kavo-labs/kavo

Made for: Claude Code.

Wrote 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.

agentmods badge for conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/kavo-labs/kavo/conventions/github.svg)](https://agentmods.dev/skills/kavo-labs/kavo/conventions)
Your own site
<a href="https://agentmods.dev/skills/kavo-labs/kavo/conventions"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/conventions/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.

agentmods 80×15 button for conventions

Your own site · 80×15
<a href="https://agentmods.dev/skills/kavo-labs/kavo/conventions"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 598 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00598
Opus 5 $0.00019 $0.00299
Sonnet 5 $0.00008 $0.00120
Haiku 4.5 $0.00004 $0.00060

Measured 4d ago against content hash d648322dfd92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

conventions 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 4d 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.

.claude/skills/conventions/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit and branch conventions

One type vocabulary is shared across three surfaces in this repo — an issue's label, its branch prefix, and the Conventional Commit prefix used for work on it:

Type Meaning Issue label
feat New capability type:feat
fix Bug fix type:fix
chore Tooling, deps, housekeeping type:chore
test Test coverage work type:test
docs Documentation type:docs
refactor Code restructuring, no behavior change type:refactor
perf Performance improvements type:perf
ci CI/build pipeline changes type:ci

Creating a branch from an issue

An issue's type: label is also its branch prefix. Off an up-to-date main:

git checkout main && git pull --ff-only
git checkout -b <type>/<issue-number>-<short-slug>

If the issue has no type: label, ask the user which one applies before branching; do not guess.

Writing commit messages

Commits follow Conventional Commits using the same type vocabulary: <type>(<scope>): <subject> (e.g. feat(core): add cursor pagination), scope optional but preferred when the change is package-scoped. Subject line under ~72 chars, imperative mood. Add a short body only when the "why" isn't obvious. A breaking change adds ! right before the colon — type(scope)!: subject — instead of (or alongside) a BREAKING CHANGE: footer.

When a change spans more than one package, comma-separate the scopes with no space — type(scope1,scope2): subject (e.g. fix(core,nest): align pagination defaults) — rather than picking one package to name or writing separate commits for what is really one logical change.

commitlint.config.mjs additionally accepts build, revert, and style as commit types, since @commitlint/config-conventional supports them out of the box. They have no issue label or branch prefix — those three surfaces stay pinned to the eight types above — so use them only for a commit message on work already branched and labeled under one of those eight.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 4d ago Changed · +13 lines d648322dfd92
  2. 7d ago First seen · 42 lines · 38 tokens per session scan A 7169f09c83f1

Subscribe to this mod's changes

conventions is a skill published in the GitHub repository kavo-labs/kavo (14 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 598 once invoked, about $0.0002 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 2026-09-02.