A vault-lint tool for checking the organisation and health of a local knowledge vault. It finds problems such as broken links, orphan pages, duplicates, missing sources, and unfinished planning items.

It is for reviewing Agent Core, project, raw-source, and output areas and suggesting focused corrective actions.

It makes structural and data-quality problems visible before they cause confusion or become harder to fix.

How TheMuleA/codex-agent-core-template configures Claude Code and Code

Reuse

Borrowing it

Nothing to install: this file belongs to TheMuleA/codex-agent-core-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TheMuleA/codex-agent-core-template/main/.agents/skills/vault-lint/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/TheMuleA/codex-agent-core-template

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/themulea/codex-agent-core-template/vault-lint/github.svg)](https://agentmods.dev/skills/themulea/codex-agent-core-template/vault-lint)

Your own site

<a href="https://agentmods.dev/skills/themulea/codex-agent-core-template/vault-lint"><img src="https://agentmods.dev/badge/skills/themulea/codex-agent-core-template/vault-lint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/themulea/codex-agent-core-template/vault-lint"><img src="https://agentmods.dev/badge/skills/themulea/codex-agent-core-template/vault-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,119 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00051	$0.01119
Opus 5.5	$0.00020	$0.00448
Sonnet 5.5	$0.00010	$0.00224
Haiku 4.5	$0.00005	$0.00112

Measured 2mo ago against content hash 1d5d0ee0fcaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vault-lint 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 2mo 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.

.agents/skills/vault-lint/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vault-lint

Назначение

Проверяет здоровье локального vault и помогает поддерживать порядок.

Lint не исправляет автоматически. Он выявляет проблемы, разделяет их по уровню риска и предлагает точечные действия через обычный change workflow.

Область проверки

Перед проверкой определить область:

Agent Core: agent/, .agents/skills/, релевантные logs.
Active project: projects/<project_id>/, project roadmaps, project pending items, project work plans и релевантные logs.
Raw/source layer: raw/.
Output layer: output/.
Structural compare scope: исходные и новые пути, если идёт структурное сравнение.

По умолчанию для project lint проверять только active project layer. Другие project layers не читать и не смешивать без отдельной причины или подтверждения пользователя.

Фактический project_id берётся из projects/index.md после выбора active project.

Что проверять

Битые внутренние ссылки.
Orphan pages.
Неактуальные страницы.
Слишком длинные content pages.
Пустые placeholder-разделы.
Planning items.
Pending items.
Необработанные источники в raw/, raw/sources/ или согласованном source inbox.
Дублирующиеся страницы.
Страницы без источников, если источники должны быть.
Data gaps — пробелы данных, которые мешают использовать страницу или раздел как рабочую базу знаний.
Соответствие страниц agent/protocols/page-conventions.md.
Соответствие источников agent/protocols/provenance-policy.md.
Соответствие связей agent/protocols/linking-policy.md.
Соответствие проверки agent/protocols/lint-checklist.md.

Lint cadence

lint cadence — ритм, в котором ты предлагаешь проверку vault. Это не автоматическое расписание и не разрешение на запуск внешних инструментов.

Ты должен предлагать vault-lint:

после серии ingest или крупного переноса данных из raw/source layer в Agent Core или project layer;
после массового создания, переноса или обновления страниц;
перед большим synthesis/query, когда вывод зависит от нескольких разделов и качества связей;
перед переходом на новый этап работы, если накопились pending items, новые источники или изменения структуры;
по прямому запросу пользователя: “проверь порядок”, “сделай lint”, “проверь базу”.

Read the full file on GitHub · 90 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.

2mo ago First seen · 90 lines · 51 tokens per session scan A 1d5d0ee0fcaf

Subscribe to this mod's changes

vault-lint is a skill published in the GitHub repository TheMuleA/codex-agent-core-template (12 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,119 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Memory and context

vault-lint next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vault-lintTheMuleA/codex-agent-core-template	Skill	12	5mo ago	MIT	A	51	Claude Code, Codex
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	74	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex

codex-agent-core-template: Skill for Claude Code