agentmods.dev

upgrade-project

upgrade-project is a skill for Claude Code, Codex from andrewcigan/vibe-dev-plugin. It costs 0 tokens per session (1,007 once invoked), scanned A, original, MIT.

A project-upgrade workflow for moving an existing Vibe Dev project to engine version 8. It supports a soft mode with warnings and a strict mode with full blocking checks, and starts with a preview that changes nothing.

In plain words
What is it for?
Use it when updating a live or older project to the current engine. It previews blocked actions, selects an enforcement mode, updates version information, and adds backup and provenance details.
Why use it?
It shows which existing project rules may fail after the upgrade and helps preserve project history while applying the newer checks.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the vibe-dev plugin — 29 skills, 24 agents, 7 hooks shipped together

not rated 5 1mo ago A scan 0 tokens original MIT
View the source file andrewcigan/vibe-dev-plugin
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/upgrade-project
Any agent
npx skills add andrewcigan/vibe-dev-plugin --skill upgrade-project
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.

agentmods badge for upgrade-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/upgrade-project.svg)](https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/upgrade-project)
Your own site
<a href="https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/upgrade-project"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/upgrade-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,007 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01007
Opus 5 $0.00000 $0.00504
Sonnet 5 $0.00000 $0.00201
Haiku 4.5 $0.00000 $0.00101

Measured 5d ago against content hash 8bc75f5bd20d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

upgrade-project 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.

skills/upgrade-project/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/upgrade-project — перевод живого проекта на актуальный движок

Зачем

При обновлении плагина движок (hooks/, схема, строгость) меняется. Живые проекты остаются «legacy» (структурные проверки = warn), пока пользователь явно не выполнит апгрейд. legacy = нет .harness/engine-version или его major ниже актуального.

Скрипт scripts/upgrade-project.sh (v8.0.1) — источник правды, у него три режима. Мажор движка берётся автоматически из plugin.json (сейчас 8).

Порядок (ВСЕГДА сначала dry-run)

  1. Подтвердить vibe-проект — есть .harness/ или feature_list.json.
  2. --dry-run ПЕРВЫМ ДЕЛОМ (ничего не пишет): 
    bash "${CLAUDE_PLUGIN_ROOT}/scripts/upgrade-project.sh" --dry-run .
    Прогоняет реальный сторож и печатает человекочитаемо: что заблокируется в строгом режиме, останется ли блок в мягком (жёсткий UI-контроль не понижается — задачи в «готово» без скриншота), сколько провенанс-этикеток проставится. Не пропускай этот шаг — иначе первая же правка feature_list упадёт постфактум (жёсткий UI-гейт B2/feat-204 строг всегда, dry-run предупреждает о нём заранее).
  3. Выбрать режим по результату dry-run:
    • Мягкий (живой проект с историей, задачи заведены задним числом без формальных доказательств): 
      bash "${CLAUDE_PLUGIN_ROOT}/scripts/upgrade-project.sh" --soft .
      Ставит движок 8 + мягкий режим (v8-проверки = подсказки, профиль strict СОХРАНЯЕТСЯ), мигрирует провенанс, создаёт бэкап-тег. Git-гейты не навязываются. Жёсткими остаются UI-скриншоты и массовый внешний API.
    • Строгий (проект приведён в порядок, готов к полным блокировкам): 
      bash "${CLAUDE_PLUGIN_ROOT}/scripts/upgrade-project.sh" --strict .
      Движок 8 + pending-strict + git pre-commit backstop. Все v8-гейты блокируют.
  4. Если dry-run показал «ОСТАНЕТСЯ БЛОК» (UI-долг) — сначала реши его (перенеси метку реального browser-прогона в layer_4_user_at, или честно понизь passing→awaiting_user_acceptance, или переснимай скриншоты), потом переводи. Не выдумывай evidence «задним числом» без реального прогона.
  5. Требование скрипта: чистое git-дерево (бэкап-точка ставится тегом). Грязное дерево → сначала закоммить. Скрипт сам дописывает .gitignore для служебных файлов харнеса.
  6. Закоммить результат осмысленным сообщением.

Read the full file on GitHub · 44 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.

  1. 5d ago First seen · 44 lines · 0 tokens per session scan A 8bc75f5bd20d

Subscribe to this mod's changes

upgrade-project is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,007 tokens. 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.

DevOps and cloudai-agentsclaude-codeclaude-code-pluginharnessvibe-coding
Related

Other skills, from other repositories

harness

하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용.

revfactory/harness · 170 tokens

kimchi

Turn a raw product idea into build-ready docs — one doc per EPIC with locked decisions, exact API contracts, a story-by-story priority plan, and an execute.md handoff Claude can build from across sessions. Gets the clarity by interrogating the user through a roster of expert personas that grill, counter, and refuse to…

chitransh-cj/kimchi · 122 tokens

compose

The mumei orchestrator. For new features, presents a vehicle picker — spec (full SDD workflow: clarification → requirements → design → tasks each auto-reviewed up to 3 iterations → single user approval → Wave-by-Wave implementation → 4-stage review) or plan (Claude Code plan-mode wrapper: hand off to plan mode…

iroha924/mumei · 213 tokens

dhpk-opsx-apply-goal

Unattended OpenSpec goal generator for an existing change-id that needs a bounded fresh-session implementation goal. Not for: authoring, applying in the current session, verifying, syncing, or archiving. Output: an analysis summary plus one pasteable /goal condition, or a hard-stop report.

hmj1026/dhpk · 70 tokens

dhpk-deploy-list

Cross-project deploy file-list generator (schema=v1). Use when: building a deploy/release checklist from git history, listing which files to ship for a deploy, 部署清單, deploy list/checklist. Scope via --anchor (in-code markers), --deploy-commits (pinned commits), or whole base..head; filters dev-only paths (tests, docs…

hmj1026/dhpk · 151 tokens

peruse

Plan-vehicle review pipeline. Runs Stage 0 detector (semgrep + osv-scanner) plus security-reviewer and adversarial-reviewer in parallel against the current diff, validates each finding via issue-validator, aggregates a verdict, and writes a review JSON to .mumei/plans/ /reviews/ .json. Triggers when the user invokes…

iroha924/mumei · 160 tokens