Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sangrokjung-session-wrap
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/session-wrap
What's inside
- Skill name
session-wrap- Description
- Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
- License
- MIT
- Instructions
- 229 lines in SKILL.md · view on GitHub
Files (7)
- SKILL.md
- output-schema.md · references/
- prompt-automation-scout.md · references/
- prompt-doc-updater.md · references/
- prompt-duplicate-checker.md · references/
- prompt-followup-suggester.md · references/
- prompt-learning-extractor.md · references/
SKILL.md (first lines)
# /session-wrap 스킬
## 파이프라인 개요
```
입력: /session-wrap [--dry-run] [--skip-docs] [--skip-learning] [--skip-scout] [--skip-followup]
[Phase 0] 컨텍스트 수집
├─ git diff --stat (이번 세션 변경사항)
├─ ~/.claude/homunculus/observations.jsonl (최근 관찰)
└─ /tmp/session-wrap/context.md 생성
[Phase 1] 병렬 4개 subagent (Explore, sonnet)
├─ doc-updater → 문서 업데이트 필요 곳 탐지
├─ automation-scout → 반복 패턴 발견 + 스킬 후보 제안
├─ learning-extractor → 배운 점 추출 (instinct 후보)
└─ followup-suggester → 다음 작업 제안
[Phase 2] 순차 1개 subagent (Explore, sonnet)
└─ duplicate-checker → Phase 1 결과 중복 제거 + 카테고리 분류
[Phase 3] AskUserQuestion으로 사용자 선택
[Phase 4] 선택된 항목만 실행
[Phase 5] 리포트 출력 + session-wrap-followups.md 기록
```
## 파라미터 파싱
사용자 입력에서 다음을 추출:
| 파라미터 | 기본값 | 설명 |
|---------|--------|------|
| --dry-run | false | 탐지만 수행, 실행하지 않음 (Phase 3에서 중단) |
| --skip-docs | false | doc-updater subagent 생략 |
| --skip-learning | false | learning-extractor subagent 생략 |
| --skip-scout | false | automation-scout subagent 생략 |
| --skip-followup | false | followup-suggester subagent 생략 |
## Phase 0: 컨텍스트 수집
세션 중 변경사항과 관찰 데이터를 수집하여 subagent에 전달할 컨텍스트를 구성한다.
```bash
# 1. Git 변경사항 수집 (git repo인 경우만)
WORK_DIR=$(pwd)
if git -C "$WORK_DIR" rev-parse --is-inside-work-tree 2>/dev/null; then
git -C "$WORK_DIR" diff --stat HEAD~5..HEAD > /tmp/session-wrap/git-changes.txt 2>/dev/null || true
git -C "$WORK_DIR" diff --name-only HEAD~5..HEAD > /tmp/session-wrap/changed-files.txt 2>/dev/null || true
git -C "$WORK_DIR" log --oneline -10 > /tmp/session-wrap/recent-commits.txt 2>/dev/null || true
fi
# 2. 관찰 데이터 수집 (최근 50개)
OBS_FILE="$HOME/.claude/homunculus/observations.jsonl"
if [ -f "$OBS_FILE" ]; then
tail -50 "$OBS_FILE" > /tmp/session-wrap/recent-observations.jsonl
fi
# 3. 버퍼 데이터 수집 (있으면)
BUFFER_FILE="$HOME/.claude/homunculus/buffer.jsonl"
if [ -f "$BUFFER_FILE" ]; then
tail -30 "$BUFFER_FILE" > /tmp/session-wrap/recent-buffer.jsonl
fi
```
`/tmp/session-wrap/` 디렉토리를 생성하고 위 수집을 실행한다.
## Phase 1: 병렬 Subagent 실행
4개 subagent를 **동시에** 실행한다. `--skip-*` 플래그로 특정 subagent를 건너뛸 수 있다.
각 subagent 프롬프트는 `references/` 디렉토리에 위치:
| Subagent | 프롬프트 파일 | 출력 파일 |
|----------|-------------|----------|
| doc-updater | `references/prompt-doc-updater.md` | `/tmp/session-wrap/results/doc-updates.json` |
| automation-scout | `references/prompt-automation-scout.md` | `/tmp/session-wrap/results/automation-patterns.json` |
| learning-extractor | `references/prompt-learning-extractor.md` | `/tmp/session-wrap/results/learning-points.json` |
| followup-suggester | `references/prompt-followup-suggester.md` | `/tmp/session-wrap/results/followup-tasks.json` |
### Subagent 실행 패턴
```
# 활성화된 subagent만 필터링
active_agents = [
("doc-updater", skip_docs 아니면),
("automation-scout", skip_scout 아니면),
("learning-extractor", skip_learning 아니면),
("followup-suggester", skip_followup 아니면),
]
# 병렬 Task 호출 (Explore, sonnet)
for agent in active_agents:
Task(
subagent_type="Explore",
prompt=Read("references/prompt-{agent}.md") + context_data
)
```
각 subagent는 결과를 JSON 파일로 `/tmp/session-wrap/results/`에 기록한다.
### 출력 JSON 스키마
모든 subagent의 출력은 동일한 아이템 스키마를 따른다:
```json
{
"items": [
{
"id": "unique-id",
"source": "doc-updater|automation-scout|learning-extractor|followup-suggester",
"title": "항목 제목",
"description": "상세 설명",
"category": "auto|user|info",
"priority": "high|medium|low",
"action": "실행할 구체적 작업 (있으면)",
"files": ["관련 파일 경로들"]
}From sangrokjung/claude-forge, MIT.
More from sangrokjung/claude-forge
- 0.776score
frontend-code-review
sangrokjung
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`).
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
systematic-debugging
sangrokjung
Structured debugging methodology — use before proposing fixes for any error or failure.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
humanize-korean
sangrokjung
Clean up translation-ese and AI-writing tics in Korean prose so it reads like a person wrote it — content (facts, numbers, proper nouns, quotes) stays 100%…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
harness-diet
sangrokjung
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
review-loop
sangrokjung
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
skill-factory
sangrokjung
Analyze session work and automatically convert reusable patterns into Claude Code skills.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
cc-dev-agent
sangrokjung
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
relay
sangrokjung
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off.
SkillBFreshness: B★ 863Claude Code +9 - 0.773score
continuous-learning-v2
sangrokjung
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
SkillBFreshness: B★ 863Claude Code +9 - 0.773score
korean-spell-check
sangrokjung
Use Nara/PNU Korean spell-check surfaces conservatively to proofread Korean text, chunk long input, and return change-focused correction suggestions.
SkillBFreshness: B★ 863Claude Code +9 - 0.772score
loop-forge
sangrokjung
Turn a one-line description of a repetitive task into a reusable, self-guarding slash command.
SkillBFreshness: B★ 863Claude Code +9 - 0.771score
dependency-upgrade
sangrokjung
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing.
SkillBFreshness: B★ 863Claude Code +9
Signals
- Stars
- 863
- Forks
- 184
- Open issues
- 22
- Last commit (this folder)
- Jun 19, 2026 (4 months ago)
- Last release
- Aug 25, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sangrokjung/claude-forge
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sangrokjung
- 0.776score
harness-diet
sangrokjung
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
relay
sangrokjung
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
cc-dev-agent
sangrokjung
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
frontend-code-review
sangrokjung
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`).
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
humanize-korean
sangrokjung
Clean up translation-ese and AI-writing tics in Korean prose so it reads like a person wrote it — content (facts, numbers, proper nouns, quotes) stays 100%…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
review-loop
sangrokjung
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until…
SkillBFreshness: B★ 863Claude Code +9
Cite this page
session-wrap skill. Agent Mart. https://agentmart.dev/skills/sangrokjung-session-wrap (last updated 2026-10-24)