A Codex workflow for maintaining a vault, meaning a stored collection of project memory and wiki content. It checks memory, cleans and indexes wiki content, refreshes search data, and reviews past Codex sessions.

Use it to run vault maintenance, update search indexes, review session learnings, and identify proposed improvements to project memory or instructions.

Stored project information can become outdated, disorganized, or hard to retrieve. This workflow checks the vault in stages while protecting isolated areas and requiring approval for destructive changes.

evolution — Skill for Claude Code and Codex by mrDesign-ww: A Codex workflow for maintaining a vault, meaning 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/mrdesign-ww/vault-os/evolution

Any agent

npx skills add mrDesign-ww/vault-os --skill evolution

Clone the repo

git clone --depth 1 https://github.com/mrDesign-ww/vault-os

Made for: Claude Code, Codex.

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/mrdesign-ww/vault-os/evolution.svg)](https://agentmods.dev/skills/mrdesign-ww/vault-os/evolution)

Your own site

<a href="https://agentmods.dev/skills/mrdesign-ww/vault-os/evolution"><img src="https://agentmods.dev/badge/skills/mrdesign-ww/vault-os/evolution.svg" alt="Measured on agentmods" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 772 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.

Model	Per session	Once invoked
Fable 5	$0.00076	$0.00772
Opus 5	$0.00038	$0.00386
Sonnet 5	$0.00015	$0.00154
Haiku 4.5	$0.00008	$0.00077

Measured 3d ago against content hash 1f6f2ecb26d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolution 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 3d 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.

shell/vault-template/.agents/skills/evolution/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vault Evolution for Codex

Единый прогон гигиены и обучения vault. Запускается по SessionStart-нуджу или вручную через $evolution. Деструктивные операции требуют явного одобрения владельца.

Как исполнять

Прочитай .vault-meta/evolution/EVOLUTION.md. Он задает фазы и общие инварианты. Для Codex используй адаптации из этого файла, если формулировки плейбука относятся только к Claude.
Соблюдай инварианты: зоны из mode.json изолированы; log.md append-only; hot.md является перезаписываемым кешем; перед пакетными правками wiki используй lock; не меняй инструкции, память или skills без предложения и одобрения; не отправляй клиентские данные наружу; retrieval запускай с --no-llm.
Выполни фазы по порядку: память, wiki hygiene, retrieval refresh, reflection.
Перед любыми предложениями из reflection примени $evolution-verifier. Сам verifier ничего не изменяет.
Обновляй .vault-meta/evolution/last-run.json только через .vault-meta/evolution/update-last-run.py, чтобы JSON всегда оставался валидным.
Заверши кратким отчетом: что исправлено, что проверено, что ожидает одобрения.

Codex-адаптации

Долговременная проектная память Codex в этом vault находится в обычных PARA-страницах wiki.
~/.codex/memories_1.sqlite является внутренним генерируемым состоянием. Evolution проверяет его только на чтение и не редактирует.
Reflection анализирует ~/.codex/sessions в формате Codex. Claude-сессии и Claude-memory не изменяются.
Gate для Codex: $evolution-verifier и затем одобрение владельца.

Команды

Codex memory audit: python3 .vault-meta/evolution/memory-audit.py --platform codex
Wiki lint: python3 .vault-meta/evolution/lint-scan.py
Codex friction scan: python3 .vault-meta/evolution/trace-scan.py --platform codex
Codex repeated procedures: python3 .vault-meta/evolution/trace-scan.py --platform codex --repeats
Wiki lock: bash scripts/wiki-lock.sh acquire .vault-meta/evolution/run, затем bash scripts/wiki-lock.sh release .vault-meta/evolution/run
Retrieval refresh: VAULT_ROOT="$PWD" bash <path-to-claude-obsidian-plugin>/bin/setup-retrieve.sh --no-llm
Codex nudge: EVOLUTION_PLATFORM=codex python3 .vault-meta/evolution/health-check.py
State update: python3 .vault-meta/evolution/update-last-run.py --platform codex --phase curator_memory=DATE --phase wiki_hygiene=DATE --phase retrieval_refresh=DATE --phase reflection=DATE --notes "SUMMARY"

Read the full file on GitHub · 38 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.

3d ago First seen · 38 lines · 76 tokens per session scan A 1f6f2ecb26d3

Subscribe to this mod's changes

evolution is a skill published in the GitHub repository mrDesign-ww/vault-os (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 772 once invoked, about $0.0004 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.

Memory and context agent-skills ai claude claude-code codex developer-tools

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens