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 agentmods add skills/andrewcigan/vibe-dev-plugin/handoffnpx skills add andrewcigan/vibe-dev-plugin --skill handoffgit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWrote 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/andrewcigan/vibe-dev-plugin/handoff)<a href="https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/handoff"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/handoff.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00064 | $0.01177 |
| Opus 5 | $0.00032 | $0.00589 |
| Sonnet 5 | $0.00013 | $0.00235 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
handoff 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/handoff
5-dimensions clean-exit. Закрывает боль «забываю что делал».
5 dimensions check
1. Build
# Проект собирается без ошибок
npm run build
# или эквивалент
2. Tests
# Все тесты зелёные (existing + новые)
npm test
3. Progress
- SESSION.md обновлён (Today / What's Done / What's In Progress / What's Next)
- feature_list.json обновлён (state changes, evidence)
- error-journal.md обновлён если были ошибки
4. Artifacts
# Нет stale temp файлов
find . -name "*.tmp" -mtime -1
find . -name ".DS_Store" -delete
# Секреты не в git
git status | grep -i "\.env\|secret\|key" || echo "✓ no secrets staged"
5. Startup
# Следующая сессия сможет запустить ./init.sh с нуля
# Симуляция:
git stash
./init.sh
git stash pop
# Если упало — что-то не в репо
Если что-то не закрыто
Запиши в SESSION.md секцию # Open Issues:
## Open Issues (handoff не чистый)
- [ ] Tests падают: <которые> — нужен fix в feat-XXX
- [ ] Build падает: <причина>
- [ ] Нет evidence для feat-YYY
Следующая /resume сразу увидит и предложит починить ДО продолжения.
Группировка ошибок этой сессии
Прочитай error-journal.md записи этой сессии (по timestamp):
- Сгруппируй по
Класс ошибки - Для каждой группы: можно ли извлечь урок?
Promotion в память
Для каждого извлекаемого урока:
Lesson scope: project
- →
~/.claude/projects/<dashed-path>/memory/feedback_<slug>.md - → Добавить строку в MEMORY.md этого проекта
Lesson scope: user
- →
~/.claude/memory/MEMORY.md(глобальная) - Например: «пользователь предпочитает state-machine over tool_use»
Lesson scope: system
- → Предложение пользователю: «Заметил системный паттерн X. Добавить в ~/CLAUDE.md? Это будет применяться во всех проектах»
- НЕ записывать без явного confirm
Финальная фраза: одной строкой пользователю:
Сессия закрыта. 3 ошибки → 2 урока для памяти:
- "concurrent_writes_to_same_file" (project) — записал в feedback_concurrent_writes.md
- "execute_dont_ask" (user) — confirm? (д/н)
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.
- 5d ago First seen · 145 lines · 64 tokens per session scan A 0567f1e61c91
handoff is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,177 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 2026-08-31.
Other skills, from other repositories
event-review
周审/记忆提炼。用干净的上下文读取事件日志与任务残留，提炼候选条目进 inbox，按阈值提议 memory/knowledge/skill 升级，并陪同用户逐条分流。当用户说"review events"、"整理记忆"、"周审"、"提炼事件"或距离上次审阅超过一周时使用。.
init-harness
在当前项目初始化 L1-L2-L3 三级记忆骨架（CLAUDE.md 常驻层、.agents/INDEX.md 索引、.agents/ 详情目录、门禁清单、模板）。当用户说"初始化 harness"、"装上三级记忆"、"init harness"、"给这个项目上记忆系统"，或新项目希望启用本插件方法论时使用。.
vibe-debugging-journal
Records resolved bugs in a persistent journal — symptom, root cause, difficulty, fix, prevention. Organized by category for future reference.
vibe-session-context-flush
Performs smart context summarization when the context window is approaching capacity. Identifies what to keep, what to summarize, and creates a compact resume state.
vibe-reflect-and-compound
Extracts learnings from completed work, feedback, or failures. Updates a persistent learnings file with capped entries. Use after receiving feedback, fixing bugs, or completing complex tasks.
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…