checkpoint

checkpoint is a skill for Claude Code, Codex from andrewcigan/vibe-dev-plugin. It costs 97 tokens per session (1,648 once invoked), scanned A, original, MIT.

A progress-saving workflow that records the current project state in files, synchronizes task statuses, archives finished information, and runs a fresh-start check.

In plain words
What is it for?
Use it at a natural stopping point to update SESSION.md, preserve the active feature and next action, rotate completed history, and test whether the project can be understood from its saved files.
Why use it?
It keeps important context under project control so work can continue after the conversation becomes too large or a new session begins.

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

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/checkpoint
Any agent
npx skills add andrewcigan/vibe-dev-plugin --skill checkpoint
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 checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/checkpoint.svg)](https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/checkpoint"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/checkpoint.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,648 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 $0.00097 $0.01648
Opus 5 $0.00048 $0.00824
Sonnet 5 $0.00019 $0.00330
Haiku 4.5 $0.00010 $0.00165

Measured 4d ago against content hash 824977fe98d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

checkpoint 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.

skills/checkpoint/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/checkpoint

Управляемое сжатие вместо рулетки. Курс владельца (c8): авто-сжатие контекста — крайняя мера у самого лимита, не рабочий инструмент. Anthropic/Manus подтверждают: держи горячий контекст малым, состояние — в файлах под своим управлением, тогда порог сжатия почти не достигается.

/checkpoint — это «сохранить игру» на естественной границе: всё важное уезжает в файлы, после чего контекст можно смело сжимать или начинать сессию заново без потери нити.

Чем отличается от /end-session: checkpoint НЕ закрывает сессию и НЕ включает closing-mode. Ты продолжаешь работать сразу после него. /end-session — это «на сегодня всё» (финальный коммит + restart-helper + выход).

Порядок (сначала руками — в файлы, потом скрипт)

Шаг 1: Перезапиши Current State в SESSION.md (c6 overwrite, НЕ append)

Блок ## Current State — это снимок «здесь и сейчас», его перезаписывают целиком, не копят:

  • Last Updated — дата-время этой сессии (не шаблон YYYY-MM-DD).
  • Active Feature — реальная фича из feature_list.json (или «нет активной» на границе волны; шаблон [feat-XXX …] не оставлять).
  • What's Next — конкретный следующий шаг (не «[Следующее действие]»).

История/завершённое сюда НЕ дублируется (это раздувает горячий контекст — L4-F1). Завершённое уходит в архив (Шаг 4).

Шаг 2: Синхронизируй feature_list.json — статусы + evidence

  • Проставь фактические state фичам этой сессии.
  • Для passing/done — впиши evidence (что и как проверено). Без evidence фича не архивируется (c10).
  • Бизнес-правку требования (изменили описание/скоуп/инвариант по ходу) фиксируй ТОЛЬКО через scripts/record-change.sh — оно запишет откуда/когда/факт замены в провенанс-лог (иначе git pre-commit заблокирует коммит, L3-F4).

Шаг 3: Дозапиши журнал/решения

Значимые решения сессии → docs/decisions/ или SESSION.md → Decisions Made. Грабли → error-journal.md.

Шаг 4: Запусти скрипт (ротация + cold-start gate)

bash "${CLAUDE_PLUGIN_ROOT}/scripts/checkpoint.sh"

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 97 tokens per session scan A 824977fe98d0

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,648 once invoked, about $0.0005 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.

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

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

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

release

Release a new version of the mumei repository. Invoke when the user gives an explicit release instruction ("release it", "/release", "patch release", "ship 0.2.0"). Takes no argument or "patch" / "minor" / "major" for a SemVer bump, or a direct version such as "0.2.0". Wraps any uncommitted changes into a single…

iroha924/mumei · 144 tokens

glean

This skill should be used BEFORE any feature design. It runs structured gleaning with the user — asking 5 high-leverage questions per round, up to 3 rounds, to extract Goal / Scope / Constraints / Edges / Done. Output is saved to .mumei/scratch/ .md and used as input for /mumei:compose. Triggers include "I want to add…

iroha924/mumei · 107 tokens

cc-whatsnew

Use when a new Claude Code version is published, when checking the changelog, or when asked "what was added recently?", "what's new in v2.1.x?", or "fetch the official new features". Reports from the official release notes / changelog in two views - an exhaustive feature summary and an applicability verdict for mumei.…

iroha924/mumei · 124 tokens