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.
curl -O https://raw.githubusercontent.com/apokamo/kaji/main/.claude/skills/issue-small-change-execute/SKILL.mdgit clone --depth 1 https://github.com/apokamo/kajiWrote 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/apokamo/kaji/issue-small-change-execute)<a href="https://agentmods.dev/skills/apokamo/kaji/issue-small-change-execute"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/issue-small-change-execute/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/apokamo/kaji/issue-small-change-execute"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/issue-small-change-execute.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 | $0.00066 | $0.04488 |
| Opus 5.5 | $0.00026 | $0.01795 |
| Sonnet 5.5 | $0.00013 | $0.00898 |
| Haiku 4.5 | $0.00007 | $0.00449 |
Grade A, and why
issue-small-change-execute 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 25d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Small Change Execute
dev-small（.kaji/wf/custom/dev/dev-small.yaml）の change / fix-change step。
Issue 本文と人間の決定事項を要件の正本とし、短い方針 → baseline scope 評価 → 実装・docs →
差分確認 → commit 前の必須検証 → commit → 報告 を 1 工程で行う。
いつ使うか
| タイミング | このスキル |
|---|---|
dev-small の change（初回・RETRY 再入）/ fix-change（review 系 RETRY 後） |
✅ |
標準 dev（dev.yaml / dev-thorough*）の実装 |
❌ /issue-implement |
docs-only（type:docs） |
❌ docs workflow |
ワークフロー内の位置: start → baseline → change → review-change → (fix-change → verify-change) → pr → close
入力
ハーネス経由（コンテキスト変数）
| 変数 | 用途 |
|---|---|
issue_id / issue_ref / step_id / verdict_path |
対象 Issue、phase（change / fix-change）、verdict 保存先 |
worktree_dir / branch_name / default_branch |
作業対象 |
cycle_count / max_iterations |
参照可 |
design_path は注入されても使わない。
手動実行（スラッシュコマンド）
$ARGUMENTS = <issue_id>
worktree_dir が無い場合だけ _shared/worktree-resolve.md で絶対パスを得る。
step_id が無い場合は verdict marker から phase を決める: review-change / verify-change の最新 RETRY が
最新 fix-change 報告より新しければ fix-change、それ以外は change
（kaji issue resolve-verdict [issue_id] --step <step> の created_at を比較）。
marker が欠落して source: "artifact" で返った場合は
ended_at を ISO 8601 の時刻として比較し、null（時刻不明）で比較が必要なら推測せず停止する。
以降の [worktree_dir] は注入値または解決した絶対パス。Bash は毎回 cd [worktree_dir] && ... で実行する。
読み込み条件
| 区分 | 読むもの | 条件 |
|---|---|---|
| 通常 | Issue 本文・labels（kaji issue view [issue_id] --json title,body,labels） |
常時 |
| 通常 | git status --porcelain / git log --oneline [default_branch]..HEAD |
常時 |
| 通常 | 直近の review 系 RETRY 報告 1 件 |
fix-change |
| 通常 | 直近の自 step RETRY 報告 1 件 |
change の RETRY 再入 |
| 条件付き | docs/reference/python/*.md |
Python コードを書く場合 |
| 条件付き | docs/dev/testing-convention.md § テストサイズ定義 / § テスト戦略の原則 |
テストを追加・変更する場合 |
| 例外 | docs/dev/baseline-check.md |
--evaluate が clean 以外、または artifact 不整合 |
| 例外 | Issue 本文が参照する人間コメント | 本文が参照している、または決定の特定に不確実さがある場合 |
| 例外 | docs/dev/workflow_completion_criteria.md § type 別に追加で確認する項目 |
bug で実ログを修正前 Red の代替にする場合 |
| 例外 | docs/dev/documentation_update_criteria.md 該当節 |
docs 影響の判断に迷う場合 |
| 例外 | 失敗した検証の関連ログ全文 | 検証失敗時 |
| 例外 | _shared/report-unrelated-issues.md | 無関係な問題を発見した場合 |
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.
- 25d ago Changed · +10 lines 2634e4ebd560
- 28d ago Changed · +2 lines 9c6e1ef60a8f
- 1mo ago First seen · 249 lines · 66 tokens per session scan A 1ad58b91bb5d
issue-small-change-execute is a skill published in the GitHub repository apokamo/kaji (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 66 tokens to every session and 4,488 once invoked, about $0.0003 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 2026-09-29.
Other skills, from other repositories
audit-trail
Full traceability from PRD to code commit through the CCPM spec-driven pipeline.
issue-tracking
Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
work
Handle issue/PR work items with worktree isolation. Triggered by "/work [issuelink|description]" to start focused work.