rep-reply

rep-reply is a skill for Claude Code from tonydzi/second-brain-starter-kit. It costs 59 tokens per session (13,388 once invoked), scanned A, original, MIT.

A workflow for finding active GitHub issues and discussions where the team has relevant practical experience, then replying with useful evidence. GitHub issues and discussions are public places where developers report problems and exchange solutions.

In plain words
What is it for?
Use it to find suitable conversations, choose the best matches, and write focused replies that may include a relevant repository.
Why use it?
It helps avoid posting generic promotional messages in unrelated places. Instead, it connects real user problems with relevant existing work and experience.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the second-brain-skills plugin — 248 skills, 1 plugin shipped together

Good fit Use it to find suitable conversations, choose the best matches, and write focused replies that may include a relevant repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tonydzi/second-brain-starter-kit/rep-reply
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.

Any agent
npx skills add tonydzi/second-brain-starter-kit --skill rep-reply
Clone the repo
git clone --depth 1 https://github.com/tonydzi/second-brain-starter-kit

Made for: Claude Code.

Or install second-brain-skills, the plugin that ships this one along with the rest of its 248 skills, 1 plugin.

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 rep-reply

README.md
[![agentmods](https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/rep-reply/github.svg)](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/rep-reply)
Your own site
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/rep-reply"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/rep-reply/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.

agentmods 80×15 button for rep-reply

Your own site · 80×15
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/rep-reply"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/rep-reply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,388 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.13388
Opus 5.5 $0.00024 $0.05355
Sonnet 5.5 $0.00012 $0.02678
Haiku 4.5 $0.00006 $0.01339

Measured 8d ago against content hash 8983c9276765, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rep-reply 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 8d 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/rep-reply/SKILL.md · 353 lines

How it starts

The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rep-reply — отвечаем людям нашим опытом

Зачем

Репутация не покупается постами в свои каналы — она складывается там, где живые инженеры уже мучаются нашей болью. Один точный ответ с артефактом в чужом треде стоит больше десяти постов в своём. Канон громкости: §1.5 (молчание требует причины) + ⛔ спам ≠ громкость (одно точное сообщение в правильную дверь, никаких вееров одинакового текста).

⭐ Шаг 0-тер — ПОЛКА × ПРОСЬБА: сперва туда, где хозяин сам просит то, что у нас лежит (anton 21.09.2026, голосом)

Ещё до людного треда: python3 ~/.claude/scripts/shelf_match.py --top 15 (0 LLM, ~5 мин API) — пересечение НАШИХ публичных репо (полка, ниши из domain.json + фразы боли в registry/github-universe/shelf_overrides.json) с живыми issue целевых репо, где внешних мержат. Печатаются только точные матчи: в тексте issue названа боль конкретного нашего репо. Даём ТОЛЬКО то, что есть на полке; ниша без репо у нас = не наша экспертиза, мимо. Первый ответ захода → лучший точный матч: ответ по существу + ссылка на репо как готовое решение, не «посмотрите наш проект». ⛔ Обязательная обратная связь по КАЖДОМУ взятому или отброшенному матчу из топ-5: shelf_match.py --verdict <url> hit|miss "почему" — miss исключается навсегда, точность печатается в следующем прогоне; без вердиктов фильтр не ужесточится (замер 21.09: уровень «ниша» дал 929 матчей, уровень «боль» — 335, из них настоящих на глаз ~⅓). Таблица для Антона: --publish → вкладка «Полка × просьбы» книги целей. 🪙 Тела топ-N issue для вердиктов НЕ читает дорогая модель: Agent(model: "sonnet") получает список url и возвращает по каждому ≤3 строки «что просят · что у нас · hit/miss с причиной»; дорогая модель только утверждает вердикты (замер 21.09: 70 тел прочитаны Fable, рельса Sonnet = 0 вызовов, причина «забыл»). Пусто → строка «полка не спрошена» в журнал и Шаг 0-бис. ⚠️ Прибора НЕТ на узле — это не «пусто», и чинить его в прогоне охоты не надо (замер 23.09, хаб: shelf_match.py не найден ни в ~/.claude, ни в _imports на глубину 4, хотя Шаг 0-тер написан 21.09). Пиши в лог skip со строкой «полка не спрошена: прибора нет на узле» и иди на Шаг 0-бис; развёртывание прибора — работа посылки/деплоя, а не охоты, иначе прогон съедает себя на инфраструктуре.

Read the full file on GitHub · 353 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. 8d ago Changed · +79 lines · -83 tokens per session 8983c9276765
  2. 12d ago Changed · -1 lines a17384d7327c
  3. 16d ago Changed · +13 lines a84c8447ac67
  4. 25d ago First seen · 262 lines · 142 tokens per session scan A e193595f313c

Subscribe to this mod's changes

rep-reply is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 13,388 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 2026-09-24.

Related

Other skills, from other repositories

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

wiki

Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…

AgriciDaniel/claude-obsidian · 84 tokens

defuddle

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

AgriciDaniel/claude-obsidian · 57 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens

wiki-mode

Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…

AgriciDaniel/claude-obsidian · 83 tokens

wiki-query

Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…

AgriciDaniel/claude-obsidian · 75 tokens