Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sangrokjung/claude-forge --skill session-wrapgit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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/sangrokjung/claude-forge/session-wrap)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/session-wrap"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/session-wrap.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.02273 |
| Opus 5 | $0.00029 | $0.01137 |
| Sonnet 5 | $0.00012 | $0.00455 |
| Haiku 4.5 | $0.00006 | $0.00227 |
Grade A, and why
session-wrap 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 4d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/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.
# 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
What ships with it
6 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.
- 4d ago First seen · 234 lines · 58 tokens per session scan A 263863afe1d4
session-wrap is a skill published in the GitHub repository sangrokjung/claude-forge (824 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 2,273 once invoked, about $0.0003 per session on Opus 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 2026-09-03.
Other skills, from other repositories
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing…
session-save
Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
handoff-create
Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.
api-design
REST API contract designer and reviewer. ALWAYS use when designing new endpoints, reviewing existing API contracts, planning API versioning, or standardizing error models. Covers resource modeling (URL/naming), HTTP method semantics, status code selection, error model consistency, pagination/filtering/sorting…