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-implement/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-implement)<a href="https://agentmods.dev/skills/apokamo/kaji/issue-implement"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/issue-implement/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-implement"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/issue-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.05039 |
| Opus 5.5 | $0.00016 | $0.02016 |
| Sonnet 5.5 | $0.00008 | $0.01008 |
| Haiku 4.5 | $0.00004 | $0.00504 |
Grade A, and why
issue-implement 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 11d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Implement
承認された設計書を契約として、Red → Green → Refactor で実装する。
いつ使うか
| タイミング | このスキルを使用 |
|---|---|
| 設計レビュー完了・承認後 | ✅ 必須 |
| 設計レビュー未完了 | ❌ 待機 |
ワークフロー内の位置: design → review-design → implement → review-code → i-dev-final-check → i-pr → close
入力
ハーネス経由（コンテキスト変数）
| 変数 | 型 | 説明 |
|---|---|---|
issue_id |
str | 正規化済み Issue ID（GitHub 数値） |
issue_ref |
str | 人間可読の Issue 参照（GitHub では #<issue_id>） |
step_id |
str | 現在のステップ ID |
手動実行（スラッシュコマンド）
$ARGUMENTS = <issue_id>
解決ルール
コンテキスト変数 issue_id が存在すればそちらを使用し、なければ $ARGUMENTS の第1引数を使う。
手動実行時の issue_ref は #<issue_id> とする。
読み込み方針（段階的開示）
開始時に implement-quickref.md だけを Read する。 正本 docs・reference・template は quickref の対応表と各 Step の指示に従い、必要になった時点で読む。
- 既読ファイルの全文再 Read はしない。必要箇所を
rg -n '^##? '等で特定し、対象セクションだけを読む。 - 全文再 Read を許すのは、(a) 現セッションに本文がない、(b) 前回 Read 後にファイルが変更された、(c) 対象範囲だけでは判断不能、のいずれかに限る。理由を作業メモに残す。
- 同じ内容を shell の
catと Read ツールの両方で取得しない。 - 規則本文は正本 docs を優先する。quickref と本 skill は規則の要約・読込タイミング・手順だけを持つ。
前提条件
/issue-start実行済み/issue-designで設計書作成済み- 設計レビュー承認済み
共通ルール
- _shared/report-unrelated-issues.md — 無関係な問題の報告ルール
実行手順
Step 1: Worktree 情報の取得
_shared/worktree-resolve.md に従って絶対パスを解決し、以降はそのパスを使う。
Step 1.5: 実行期限の確認
agent step の hard deadline は延長されず、到達時点で verdict_path が未保存なら harness が session を
強制終了する（正本: workflow-authoring.md § timeout と attempt deadline）。
正常に前進していても期限切れで進捗が失われないよう、次の規則で残時間を管理する。
- 開始時: コンテキスト変数
attempt_deadline_utc/step_timeout_secondsを記録する。 変数がない（手動実行等）場合は本 Step の規則を適用しない。 - 前 attempt の checkpoint の引継ぎ: 次の条件をすべて満たす直近コメントを checkpoint コメントとして扱い、
その「残作業」から再開する（implement の self-RETRY は
resume:を持たず fresh session のため、引継ぎ情報は Issue コメントと worktree が唯一の経路）。- body 1 行目が
<!-- kaji-verdict: step=implement status=(RETRY|ABORT) --> - 2 行目以降に見出し
## 期限前 checkpoint（implement）を持つ（手順 7 で付与。期限と無関係な ABORT コメントを引継ぎ元と誤認しないための識別子） - それより後に
step=implementのPASS/BACKmarker コメントがない
- body 1 行目が
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.
- 11d ago Changed 807adfcb26d2
- 25d ago Changed · +60 lines c40710d1faee
- 29d ago Changed 950d23c20712
- 1mo ago First seen · 223 lines · 41 tokens per session scan A 6354fd736b4e
issue-implement is a skill published in the GitHub repository apokamo/kaji (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 41 tokens to every session and 5,039 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
superpowers-test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
implement
Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.