stream-timecodes

A tool that creates chapter markers for streams, podcasts and videos from a VTT transcription file. VTT is a subtitle format containing timed pieces of spoken text.

In plain words
What is it for?
It helps process a VTT file and produce 18 timestamped topic descriptions in the format hours:minutes:seconds, with concise descriptions.
Why use it?
It turns a full transcription into a short list of named points in the recording, so viewers can find important sections more easily.

Skill for Claude CodeCodex

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/howdeploy/kisa-stack/stream-timecodes
Any agent
npx skills add howdeploy/kisa-stack --skill stream-timecodes
Clone the repo
git clone --depth 1 https://github.com/howdeploy/kisa-stack

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 984 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 $0.00071 $0.00984
Opus 5 $0.00036 $0.00492
Sonnet 5 $0.00014 $0.00197
Haiku 4.5 $0.00007 $0.00098

Measured yesterday against content hash acbe346e01c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stream-timecodes 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/process_vtt.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/stream-timecodes/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stream Timecodes

Автоматическое создание таймкодов для стримов, подкастов и видео из VTT-файлов транскрипции.

Входные данные

  • VTT файл с транскрипцией (любая длительность)
  • Путь к файлу через вложение в Telegram или прямой путь

Выходные данные

18 таймкодов в формате:

ЧЧ:ММ:СС - Краткое описание темы

Правила форматирования

КРИТИЧНО: Букву "ё" НЕ использовать!

  • Всегда заменять "ё" на "е"
  • ❌ "всё" → ✅ "все"
  • ❌ "ещё" → ✅ "еще"
  • ❌ "трёхчасовой" → ✅ "трехчасовой"

Формат таймкодов

  • Временная метка: ЧЧ:ММ:СС (всегда с ведущими нулями)
  • Разделитель: - (пробел-тире-пробел)
  • Описание: краткое, емкое, без "ё"
  • Длина описания: 30-70 символов

Стиль описаний

  • Без точки в конце
  • Начинать с заглавной буквы
  • Избегать общих фраз типа "Обсуждение темы"
  • Конкретика: упоминать ключевые моменты, имена, технологии
  • Без излишних подробностей

Процесс работы

  1. Получить VTT файл от пользователя
  2. Запустить обработку через скрипт scripts/process_vtt.py
  3. Проанализировать сегменты и выделить 18 ключевых моментов
  4. Создать описания для каждого таймкода (краткие, без "ё")
  5. Отправить в чат текстовым сообщением (НЕ файлом!)

Использование скрипта

python3 scripts/process_vtt.py /path/to/file.vtt

Скрипт выводит базовую разметку по 5-минутным интервалам. На основе этого вывода:

  • Выбери 18 самых важных моментов
  • Равномерно распредели по длительности
  • Создай краткие описания тем

Пример вывода

00:00:00 - Стартуем, приветствия
00:05:00 - История создания продукта на AI
00:10:00 - Колоссальный скачок в развитии AI
00:15:00 - Путь в вайбкод: от Linux до первых лендингов
00:20:00 - Deep research и база знаний через нейронки
00:25:00 - Разочарование в крипте
00:30:00 - AI растет, крипта стоит
00:35:00 - Промпт-инженеры и автоматизация
00:40:00 - AI vs человеческие навыки
00:45:00 - Регуляция AI неизбежна
00:50:00 - Китайские модели без цензуры
00:55:00 - Инструменты и RAG: много хайпа
01:00:00 - AI-агенты в реальности
01:05:00 - Оркестрация суб-агентов
01:10:00 - Почему Claude Code — лучший инструмент
01:15:00 - Безопасность AI-решений
01:20:00 - E-commerce проект и GigaChat
01:25:00 - Русские нейронки: катастрофа

Read the full file on GitHub · 96 lines

Files

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.

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. yesterday First seen · 96 lines · 71 tokens per session scan A acbe346e01c8

Subscribe to this mod's changes

stream-timecodes is a skill published in the GitHub repository howdeploy/kisa-stack (23 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 984 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens