Session Initialization

VerifiedSafe

Automatically checks environment (git status, plans, roles) and task status when starting a coding session. Provides a summary of current branch, priority tasks from Plans.md, and important notes from AGENTS.md. Use at session start to quickly understand context and next actions.

Sby Skills Guide Bot
ProductivityBeginner
2/28/2026
Claude Code
#session-start#task-tracking#git-status#workflow#context-restore

Recommended for

Automated summary

At the start of a session, this skill checks the environment (Git, Plans.md, AGENTS.md) and produces a concise report of ongoing tasks and project constraints.

Strengths

  • Runs Git, Plans.md and AGENTS.md checks in parallel for a fast status snapshot
  • Detects in-progress work (cc:WIP, pm:依頼中, cc:TODO) and surfaces it in a formatted report
  • Warns when tracking files grow too large (Plans.md over 200 lines, session-log.md over 500 lines) and suggests cleanup
  • Optionally pulls past session context from Claude-mem when that tool is configured

Limitations

  • Tightly coupled to a specific project convention (Plans.md, AGENTS.md, cc:/pm: markers) that must already be in place
  • The Claude-mem step is skipped entirely when the tool is absent, so historical context is conditional
  • Performs no actual work: it only reports state and proposes a next step
When to use it

Use it at the very beginning of a work session to see where things stand and which project rules apply.

When not to use it

Avoid it during implementation, code review, or mid-session work, since it is meant only for initialization.

Security analysis

Safe
Quality score85/100

The skill only uses Read/Bash for local inspection commands such as git status, wc, cat, head, and optionally reading Claude-mem mode from a local settings file. It does not delete data, exfiltrate secrets, download/execute remote payloads, or disable safety mechanisms. Bash is used for legitimate read-only session-status checks.

No concerns found

How this analysis is made

Examples

Start the day
start session — what should I work on today?
Status check
状況を確認して。今のブランチと優先タスクを教えて
Resume interrupted work
セッション開始。前回の続きから再開したいので、Plans.md の WIP タスクを確認して

name: session-init description: "Initializes session with environment check and task status overview. Use when user mentions セッション開始, 作業開始, 状況確認, what should I work on, start session. Do NOT load for: 実装作業, レビュー, セッション途中の作業." allowed-tools: ["Read", "Write", "Bash"] user-invocable: false metadata: skillport: category: core tags: [session, init, startup, status] alwaysApply: false

Session Init Skill

セッション開始時の環境確認と現在のタスク状況把握を行うスキル。


トリガーフレーズ

このスキルは以下のフレーズで起動します:

  • 「セッション開始」
  • 「作業開始」
  • 「今日の作業を始める」
  • 「状況を確認して」
  • 「何をすればいい?」
  • "start session"
  • "what should I work on?"

概要

Session Init スキルは、Claude Code セッション開始時に自動的に以下を確認します:

  1. Git 状態: 現在のブランチ、未コミットの変更
  2. Plans.md: 進行中タスク、依頼されたタスク
  3. AGENTS.md: 役割分担、禁止事項の確認
  4. 前回セッション: 引き継ぎ事項の確認

実行手順

Step 0: ファイル状態チェック(自動整理)

セッション開始前にファイルサイズをチェック:

# Plans.md の行数チェック
if [ -f "Plans.md" ]; then
  lines=$(wc -l < Plans.md)
  if [ "$lines" -gt 200 ]; then
    echo "⚠️ Plans.md が ${lines} 行です。「整理して」で整理を推奨"
  fi
fi

# session-log.md の行数チェック
if [ -f ".claude/memory/session-log.md" ]; then
  lines=$(wc -l < .claude/memory/session-log.md)
  if [ "$lines" -gt 500 ]; then
    echo "⚠️ session-log.md が ${lines} 行です。「セッションログを整理して」で整理を推奨"
  fi
fi

整理が必要な場合は提案を表示(作業には影響しない)。

Step 0.5: Claude-mem 文脈確認(オプション)

Claude-mem が有効な場合、過去の文脈を自動表示:

# Claude-mem の状態チェック
if [ -f "$HOME/.claude-mem/settings.json" ]; then
  mode=$(cat ~/.claude-mem/settings.json | grep -o '"CLAUDE_MEM_MODE"[^,}]*' | cut -d'"' -f4)
  if [ "$mode" = "harness" ] || [ "$mode" = "harness--ja" ]; then
    echo "📚 Claude-mem (harness モード) が有効です"
  fi
fi

Claude-mem 有効時に表示する内容:

  1. 過去のガードレール発動:

    • mem-search で guard タイプの観測を検索
    • 「このプロジェクトでは過去 N 回テスト改ざんを防止」
  2. 直近の作業サマリー:

    • 最新のセッションサマリーを表示
    • 「前回: Feature X の設計完了」
  3. 継続タスクの提案:

    • Plans.md と組み合わせて次のアクションを提案
## 📚 過去の文脈(Claude-mem)

**ガードレール履歴**:
- テスト改ざん防止: 2回

**前回のセッション**:
- Feature X 設計完了
- RBAC 採用を決定

**💡 継続推奨**: Plans.md の「Feature X 実装」から開始

注: Claude-mem が未設定の場合、このステップはスキップされます。

Step 1: 環境確認

以下を並列で実行:

# Git状態
git status -sb
git log --oneline -3
# Plans.md
cat Plans.md 2>/dev/null || echo "Plans.md not found"
# AGENTS.md の要点
head -50 AGENTS.md 2>/dev/null || echo "AGENTS.md not found"

Step 2: タスク状況の把握

Plans.md から以下を抽出:

  • cc:WIP - 前回から継続中のタスク
  • pm:依頼中 - PM から新規依頼されたタスク(互換: cursor:依頼中)
  • cc:TODO - 未着手だが割り当て済みのタスク

Step 3: 状況レポートの出力

## 🚀 セッション開始

**日時**: {{YYYY-MM-DD HH:MM}}
**ブランチ**: {{branch}}

---

### 📋 今日のタスク

**優先タスク**:
- {{pm:依頼中(互換: cursor:依頼中) または cc:WIP のタスク}}

**その他のタスク**:
- {{cc:TODO のタスク一覧}}

---

### ⚠️ 注意事項

{{AGENTS.md からの重要な制約・禁止事項}}

---

**作業を開始しますか?**

出力フォーマット

セッション開始時は、以下の情報を簡潔に提示:

| 項目 | 内容 | |------|------| | 現在のブランチ | staging など | | 優先タスク | 最も重要な 1-2 件 | | 注意事項 | 禁止事項の要約 | | 次のアクション | 具体的な提案 |


関連コマンド

  • /work - タスク実行(並列実行対応)
  • /sync-status - Plans.md の進捗サマリー
  • /cleanup - ファイルの自動整理

注意事項

  • AGENTS.md を必ず確認: 役割分担を把握してから作業開始
  • Plans.md が無い場合: /harness-init を案内
  • 前回の作業が中断している場合: 継続するか確認

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/session-initialization-mm5t8ba4/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/session-initialization-mm5t8ba4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/session-initialization-mm5t8ba4/download' --output '.skill-downloads/session-initialization-mm5t8ba4/SKILL.md.part' && mv '.skill-downloads/session-initialization-mm5t8ba4/SKILL.md.part' '.skill-downloads/session-initialization-mm5t8ba4/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/session-initialization-mm5t8ba4/SKILL.md' && test -s '.skill-downloads/session-initialization-mm5t8ba4/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/session-init' && cp -R '.skill-downloads/session-initialization-mm5t8ba4' '.claude/skills/session-init'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/session-initialization-mm5t8ba4'

openskills read 'session-initialization-mm5t8ba4'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/session-initialization-mm5t8ba4/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills