dev-log

dev-log is a skill for Claude Code from masa-san-jp/Agent-Aiko. It costs 0 tokens per session (1,122 once invoked), scanned A, original, MIT.

A development-log skill that appends session entries to a JSON Lines log and creates documentation files in a specified directory. JSON Lines is a text format with one JSON record per line.

In plain words
What is it for?
Recording completed or ongoing tasks, writing meeting notes, and creating dated development documents.
Why use it?
It keeps development work and decisions recorded in a consistent place instead of relying on memory or scattered notes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is 1. ../Agent-Lab/Agent-team/agents/aiko/dev-docs/ に議事録ファイルを作成(YYYY-MM-DD-<slug>.md).

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 dev-log

README.md
[![agentmods](https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/dev-log.svg)](https://agentmods.dev/skills/masa-san-jp/agent-aiko/dev-log)
Your own site
<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/dev-log"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/dev-log.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,122 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01122
Opus 5 $0.00000 $0.00561
Sonnet 5 $0.00000 $0.00224
Haiku 4.5 $0.00000 $0.00112

Measured 5d ago against content hash 9d28b3f0fe21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dev-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 5d 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/dev-log/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-log — 開発ログ記録スキル

../Agent-Lab/Agent-team/agents/aiko/dev-docs/dev-log.jsonl への追記と、../Agent-Lab/Agent-team/agents/aiko/dev-docs/ へのドキュメント作成を担います。


自動トリガー(提案)

以下の場面では、このスキルの実行を自動的にユーザーへ提案します:

  • ユーザーが作業終了を宣言したとき(「終わり」「以上」「今日はここまで」「お疲れ」など)
  • ユーザーが「議事録を作って」「ログを残して」「記録して」と言ったとき

提案内容:

「議事録と dev-log を記録しますか?
  1. ../Agent-Lab/Agent-team/agents/aiko/dev-docs/ に議事録ファイルを作成(YYYY-MM-DD-<slug>.md)
  2. dev-log.jsonl に本セッションのタスクを追記
  両方まとめて行います。よろしければ「はい」とお伝えください。」

モード1: dev-log.jsonl 追記

セッション終了時や作業の節目に実行します。

手順

  1. 今日の日付を確認(date +%Y-%m-%d
  2. 会話の文脈からタスク名・ステータス・サマリーを特定(不明な場合はユーザーに確認)
  3. 以下のフォーマットで1行末尾に追記:
{"ts":"YYYY-MM-DD","project":"Agent-Aiko","task":"<タスク名>","status":"completed|in_progress|blocked","summary":"実施内容を1〜2文で","issues":[],"decisions":[]}
  1. 追記内容をユーザーに確認表示する

必須ルール

  • ts今日の日付YYYY-MM-DD)— 省略・過去日付・未来日付は不可
  • summary は1〜2文で完結させる
  • issues / decisions は省略不可(空配列 [] でよい)
  • タスクが複数あれば 1タスク1行 で追記する

モード2: Agent-Lab 側 dev-docs/ へのドキュメント作成

議事録・設計メモ・調査結果などを ../Agent-Lab/Agent-team/agents/aiko/dev-docs/ に新規作成するときに実行します。

ファイル命名規則(必須)

YYYY-MM-DD-<slug>.md
  • YYYY-MM-DD作成日(今日の日付)
  • <slug> はケバブケース(英数字・ハイフンのみ)
  • 例: 2026-04-29-claude-rule-separation.md

日付プレフィックスは省略不可。 省略されたファイルは受け付けない。

手順

  1. 今日の日付を確認(date +%Y-%m-%d
  2. ファイル名を YYYY-MM-DD-<slug>.md 形式で決定する
  3. ファイルを ../Agent-Lab/Agent-team/agents/aiko/dev-docs/ 直下に作成する
  4. ../Agent-Lab/Agent-team/agents/aiko/dev-docs/README.md のファイル一覧テーブルに追記する
  5. dev-log.jsonl にも1行追記する(モード1のフォーマットで)

議事録の構成(標準テンプレート)

# 議事録:<テーマ>(YYYY-MM-DD)

## 概要
<1〜2文で何をしたか>

## 変更内容
<変更点を箇条書きまたは見出しで>

## 意思決定
<今後の運用に影響する判断・合意事項>

---
*作成日: YYYY-MM-DD*

ドキュメント更新時のリネーム

既存ファイルを大幅に更新した場合は、日付を更新する。git mvAgent-Lab リポ内で、リポ基準の相対パスで実行する:

cd ../Agent-Lab
git mv Agent-team/agents/aiko/dev-docs/2026-04-27-design.md Agent-team/agents/aiko/dev-docs/2026-05-01-design.md

共通: 完了後の操作

追記・作成後は ../Agent-Lab/ 内で commit & push してください:

Read the full file on GitHub · 112 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. 5d ago First seen · 112 lines · 0 tokens per session scan A 9d28b3f0fe21

Subscribe to this mod's changes

dev-log is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,122 tokens. 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.