kaji: Skill for Claude Code

.claude/skills/update-starter/SKILL.md

update-starter is a skill for Claude Code from apokamo/kaji. It costs 32 tokens per session (1,063 once invoked), scanned A, original, Apache-2.0.

A maintainer-only workflow for updating a managed starter repository to match a published kaji software release, while preparing an unpushed candidate for review.

In plain words
What is it for?
Use it to compare releases, classify all changes, update the starter’s local main branch, run its quality checks, and record the evidence in a tracking issue.
Why use it?
It prevents missed changes, inconsistent release or dependency references, and accidental updates from being pushed before review.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is apokamo/kaji's own configuration. It tells Claude Code how to work on kaji 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 kaji configures →

Reuse

Borrowing it

Nothing to install: this file belongs to apokamo/kaji. 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/apokamo/kaji/main/.claude/skills/update-starter/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/apokamo/kaji

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 update-starter

README.md
[![agentmods](https://agentmods.dev/badge/skills/apokamo/kaji/update-starter.svg)](https://agentmods.dev/skills/apokamo/kaji/update-starter)
Your own site
<a href="https://agentmods.dev/skills/apokamo/kaji/update-starter"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/update-starter.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,063 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 $0.00032 $0.01063
Opus 5 $0.00016 $0.00531
Sonnet 5 $0.00006 $0.00213
Haiku 4.5 $0.00003 $0.00106

Measured 3d ago against content hash 1e8b11acc38d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

update-starter 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 3d 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/update-starter/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Starter

kaji 側の starter-sync tracking Issue を正本として、対象 release 間の変更を全件 3 区分し、 managed starter の local main に review 前の candidate を作る maintainer 専用 skill。

入力

/update-starter <tracking_issue_id>。Issue 本文(v1 schema)から starter_repo、 任意の starter_path を読む。今回追随する target は Issue 本文を直接読まず、 kaji starter task-planactive_target(batch 内 target の最大値)から決定的に求める (starter sync runbook)。 通常 path は kaji main worktree の sibling ../<repo-name>。remote identity が starter_repo と一致しなければ ABORT。

実行順

  1. runbook の前提と managed starters 表を確認する。tracking Issue 本文が v1 schema (<!-- kaji-starter-sync: v1 -->)であること、対象 starter checkout と remote identity を 検証する。
  2. kaji starter task-plan を実行し、Issue 番号・状態・本文(completion は渡さない)を 観測として渡す。decision: SYNCactive_target を今回の target、covered_targets を 今回束ねて追随する対象集合とする。
    • route 2(新しい batch を開始)の場合、next_body(対象行を syncing + 新 batch id にした 本文)を candidate 作成より前に Issue 本文へ適用する(本文更新 → candidate 作成 → marker 付き報告、の順序を守る。部分失敗時に同じ batch を安全に再開できるようにするため)。
    • route 1(既存 batch を継続)の場合、Issue 本文は変更しない(進行中の証跡を保護する)。
    • decision: ABORT は fallback せず停止する(自動選択・自動統合をしない)。 最新の公開済み starter GitHub Release tag を開始点にする。開始点の Release 不在、 tag / Release / dependency pin の矛盾があれば ABORT。
  3. この時点で初めて classification guide を読み、開始点から active_target までの CHANGELOG、commit、changed assets を全件 3 区分する。dependency / lockfile 更新だけで完了と判定しない。
  4. starter の remote main と同期した local main に区分 (1) だけを直接 commit する。 feature branch / worktree / PR / merge は使わず、review 前に push しない。
  5. repository 実体から manifest、lockfile、quality gate を解決して実行する。Python 固有名を 前提にしない。update-starter / review-starter-update / release-starter 自身は starter に コピーしない。
  6. 3 区分表、根拠、target(= active_target)、base SHA、candidate SHA、quality gate を同じ tracking Issue に報告する。区分 (1) が空なら commit を作らず base == candidate と N/A 根拠を報告する。

Guardrails

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file 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.

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. 3d ago Changed · +12 lines 1e8b11acc38d
  2. 8d ago First seen · 54 lines · 32 tokens per session scan A eb2d575894a2

Subscribe to this mod's changes

update-starter is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 1,063 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 2026-08-30.