A project-resumption workflow for picking up work after a break. It checks that the project’s safeguards are active, compares the current state with the previous session, and rebuilds the working context.

Use it when returning to a project after days or weeks away, or when continuing an interrupted task. It asks a fresh reviewer five questions to test whether the project context is clear.

It reduces the time spent remembering what the project does, what was in progress, and whether its checks still work after an absence.

resume — Skill for Claude Code and Codex by andrewcigan: A project-resumption workflow for picking up work after a…

Install

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.

agentmods

npx agentmods add skills/andrewcigan/vibe-dev-plugin/resume

Any agent

npx skills add andrewcigan/vibe-dev-plugin --skill resume

Clone the repo

git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin

Made for: Claude Code, Codex.

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/resume.svg)](https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/resume)

Your own site

<a href="https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/resume"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/resume.svg" alt="Measured on agentmods" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,125 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.01125
Opus 5	$0.00031	$0.00562
Sonnet 5	$0.00012	$0.00225
Haiku 4.5	$0.00006	$0.00112

Measured 5d ago against content hash 59797a999a6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

resume scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/projects/<dashed-path>/memory/MEMORY.md

skills/resume/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.

/resume

Подхват проекта после паузы. Закрывает боль «вернулся через неделю — не помню что делал».

Что происходит

Шаг 0: Enforcement жив? (v6.2 F2)

P="$(cat .harness/profile 2>/dev/null)"; HB=.harness/hooks-heartbeat
case "$P" in pending-*) echo "❌ профиль $P не подтверждён живым хуком — enforcement НЕ активен"; esac
[ -f "$HB" ] && [ $(( $(date +%s) - $(awk '{print $1;exit}' "$HB") )) -le 1800 ] \
  || echo "❌ heartbeat несвежий/отсутствует — хуки в этой сессии НЕ работают"
ls .harness/hook-crashes/ 2>/dev/null && echo "⚠️ сторожа падали в прошлых сессиях — см. /doctor"

Любая строка с ❌ → СНАЧАЛА /doctor и починка активации, потом resume. Продолжать с мёртвыми сторожами = строгость только на бумаге.

Шаг 1: Cold-start test (внешний evaluator)

Запусти subagent (Sonnet, fresh context, не видит .harness/assessment.json) с инструкцией:

Прочитай только: CLAUDE.md, feature_list.json, SESSION.md, domain-rules.yaml, 
docs/PRODUCT.md (если есть), error-journal.md (если есть).

Ответь на 5 вопросов из .harness/cold-start.yaml (или templates если файла нет):
1. Что это за продукт и для кого?
2. Какой сейчас bottleneck по 7-tuple?
3. Какая фича active + verification_command?
4. Какие 3 последних архитектурных решения и почему?
5. Какие anti-patterns (что НЕ делать)?

Грейдинг: 1-5 по каждому. Pass threshold = 4/5.

Шаг 2: Анализ результата

Pass (≥4/5): state здоров, продолжаем
Fail (<4/5): state разъехался — нужен /handoff recovery + спросить пользователя что было

Шаг 3: Diff с прошлой сессией

# Последний git commit
git log -1 --format='%h %ai %s'

# Что менялось с last_session
LAST_SESSION_END=$(grep "Last Updated" SESSION.md | head -1)
git log --since="$LAST_SESSION_END" --oneline

Шаг 4: Прочитать error-journal (если есть)

Если error-journal.md существует — прочитай последние 5 записей. Это для context awareness — какие грабли уже найдены.

Шаг 5: Прочитать memory проекта

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.

5d ago First seen · 112 lines · 62 tokens per session scan B 59797a999a6e

Subscribe to this mod's changes

resume is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,125 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context ai-agents claude-code claude-code-plugin harness vibe-coding

dhpk-opsx-load-context

Load opsx-apply-resume Resume Phase context via a 3-tier fallback (claude-mem pinned obs → compact JSON → handoff summary), optionally fetching cross-session observations. Use when: opsx-apply-resume enters Resume Phase Steps 1b–1d. Not for: saving observations (use dhpk-opsx-post-observation) or goal generation (use…

hmj1026/dhpk · 116 tokens

dhpk-opsx-post-observation

Post a session observation to claude-mem from opsx-apply-resume Save Phase — builds a JSON payload and runs post-obs.sh as a non-blocking background post (the caller collects the result before the handoff write, so the POST overlaps Save-Phase Steps 4–6). Use when: opsx-apply-resume Save Phase Step 3b, right after…

hmj1026/dhpk · 148 tokens

resume