Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bestdeejay-design/agent-skillsnpx agentmods add skills/bestdeejay-design/agent-skills/doc-compareWrote 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.
[](https://agentmods.dev/skills/bestdeejay-design/agent-skills/doc-compare)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/doc-compare"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/doc-compare/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.
<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/doc-compare"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/doc-compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00264 | $0.01242 |
| Opus 5.5 | $0.00106 | $0.00497 |
| Sonnet 5.5 | $0.00053 | $0.00248 |
| Haiku 4.5 | $0.00026 | $0.00124 |
Grade A, and why
doc-compare 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Compare
Визуальное сравнение markdown-документов с подсветкой правок: две колонки (слева/справа) в одном окне браузера, вкладки на каждую пару, изменённые места подсвечены, кнопка «Только изменения».
🎯 When to use
- Нужно визуально сравнить локальный драфт с опубликованной версией (оферты
lovii_docsvsaxiiom-ru/lovii). - Сразу видеть, ГДЕ были правки: изменённые блоки подсвечены, внутри — пословно.
- Свернуть всё лишнее кнопкой «Только изменения» и смотреть только затронутые места.
📦 Files
SKILL.md— этот файлscripts/compare_docs.py— сборщик side-by-side с подсветкой правок
🧰 Usage
# Локальный драфт vs опубликованное в публичном репо (gh: подтягивает через gh api)
python3 ~/.config/opencode/skills/doc-compare/scripts/compare_docs.py \
--pair "Опубликовано|gh:axiiom-ru/lovii@main:docs/Публичная_оферта.md|Драфт|./docs/Публичная_оферта.md" \
--pair "Опубликовано|gh:axiiom-ru/lovii@main:docs/Оферта_присоединения.md|Драфт|./docs/Оферта_присоединения.md"
# Построчная таблица difflib (альтернатива бок-о-бок)
python3 ~/.config/opencode/skills/doc-compare/scripts/compare_docs.py \
--diff --pair "Старая|a.md|Новая|b.md"
# Не открывать браузер, только сгенерировать файл
python3 ~/.config/opencode/skills/doc-compare/scripts/compare_docs.py --no-open --pair "L|l.md|R|r.md" --out /tmp/cmp.html
Формат --pair: "ЛеваяМетка|левый_файл|ПраваяМетка|правый_файл".
Префикс gh:owner/repo@ref:path у любого из файлов = подтянуть из GitHub через gh api (ветка ref необязательна, по умолчанию main).
🔬 Как читать результат
- Без
--diff: две колонки. Слева = первая версия (обычно опубликованная/старая), справа = вторая (драфт/новая).- 🟥 красная полоса слева — блок удалён или изменён (старое слово зачёркнуто).
- 🟩 зелёная полоса справа — блок добавлен или изменён (новое слово подсвечено).
- Внутри изменённого блока слова подсвечены пословно.
- Кнопка «Только изменения» (в шапке) прячет всё неизменённое — остаются только затронутые места.
- С
--diff: классическая таблица difflib — добавленные строки зелёные, удалённые красные, изменённые жёлтые.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +8 lines fd58eace87a2
- 1mo ago First seen · 54 lines · 264 tokens per session scan A 834f980c0f75
doc-compare is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 264 tokens to every session and 1,242 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
atelier-setup
Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.
nextcloud-files
Browse and manage Nextcloud files and folders over WebDAV via the nextcloud-agent MCP server — list a directory, read/download a file, upload, create/delete/move/copy, and read properties. Use when the agent must navigate a Nextcloud file tree, fetch a document's bytes, or reorganize storage. Do NOT use for sharing…
obsidian-organizer
File new notes into the right folder and audit/reorganize folder structure in the user's Obsidian vault, using the obsidian CLI and a single source-of-truth map note (00Index/FolderMap.md) that lives inside the vault. Use this whenever a note needs to be placed, filed, sorted, or moved into the vault; whenever the…
obsidian-vault-builder
Use when adding/editing/querying content in an existing Obsidian vault, configuring plugins, integrating Claude Code with Obsidian via Local REST API or CLI, automating ongoing capture/organization/retrieval, designing a personal knowledge management workflow, OR building academic study vaults (course prep…
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.
notes
A note-management guide for searching, reading, creating, and adding content to personal notes through an API.