agentmods.dev

local-llm-wave

local-llm-wave is a skill for Claude Code from tonydzi/second-brain-starter-kit. It costs 313 tokens per session (1,216 once invoked), scanned A, original, MIT.

A coordinated outreach procedure for sending pull requests and issue-based proposals to multiple open-source large language model vendors. A pull request is a proposed code change submitted to a repository for review.

In plain words
What is it for?
It is for finding current opportunities across LLM ecosystems, matching proposals to open issues, tracking replies, and continuing unfinished vendor conversations.
Why use it?
It prevents outreach from relying on stale issue lists or forgotten replies. It checks whether each target is still active and keeps each vendor’s work in a separate session.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

not rated 9repo +1 today A scan 313 tokens original MIT

Good fit It is for finding current opportunities across LLM ecosystems, matching proposals to open issues, tracking replies, and continuing unfinished vendor conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tonydzi/second-brain-starter-kit/local-llm-wave
View source ↗ tonydzi/second-brain-starter-kit
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 local-llm-wave
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 local-llm-wave

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/local-llm-wave"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/local-llm-wave.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 313 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,216 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 $0.00313 $0.01216
Opus 5.5 $0.00125 $0.00486
Sonnet 5.5 $0.00063 $0.00243
Haiku 4.5 $0.00031 $0.00122

Measured 25d ago against content hash 2bf4847bfb0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-llm-wave 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 25d 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/local-llm-wave/SKILL.md · 32 lines

What it actually says

LLM_WAVE — волна аутрича топ-LLM вендорам отдельными сессиями (anton 27.07)

ЦЕЛЬ: конвейер Миссии №2 — регулярно и стандартно заходить во все живые экосистемы топ-10 LLM через issue-matching, каждый вендор = своя сессия, хвосты не теряются.

ШАГИ:

  1. RECALL ПОСТРОЕННОГО (0 токенов сперва): MEMORY.md-строки 🚀 (наши PR + статусы) → [[oss-backlog-multi-vendor-wave2]] (живые двери + скипы с причинами) → дашборд $OBSIDIAN_VAULT/_Dashboards/LLM-Cookbook-Radar.html → открытые DR по волне (dr_registry). НЕ предлагать вендора из скип-листа, не проверив, что причина скипа устарела.

  2. ПРЕРЫВАНИЕ-ЧЕК (правило №1): живые ответы людей на наши открытые PR (gh pr view по реестру / pr_watch). Есть ответ → сперва он (same-day), волна после.

  3. LIVENESS-ВЕТО на каждый анкер-кандидат СЕГОДНЯ (память ≠ живое состояние): gh issue view <n> --repo <vendor/repo> --json state,title — анкер OPEN? конкурирующий PR не появился? репо мержит внешние PR (последние merged)? Радар протух (>7 дней) → сперва ~/llm-cookbook-radar/scan2.sh. ⚠️ Грабли: GitHub search >5 OR = молча 0; Google Copybara — «closed unmerged» бывает влит (читать комменты).

  4. ВЫБОР ЦЕЛЕЙ ВОЛНЫ по правилам (все = канон, не вкус):

    • только issue-matched анкер (чья-то живая просьба; без анкера = антипаттерн, в бэклог);
    • первый PR в НОВУЮ экосистему > второго в старую; один репо не флудить (ждать ревью);
    • только порты ГОТОВЫХ наших паттернов (authority routing #787, consensus #784, pipeline-vs-barrier #788, citation #789, verified-ops #70) + живой прогон; новьё с нуля = не волна;
    • потолок ~3 пишущих сессии за раз (§9.2).

  5. СИД ОТДЕЛЬНОЙ СЕССИИ на каждого вендора (spawn_task, cwd=~/chips-playground — из GDrive-workdir падает WorktreeCreate): сид самодостаточен — Outcome (PR закрывает issue #N) · Контекст (анкер-линк, наш паттерн-источник, прецеденты репо, CONTRIBUTING/CLA-грабли) · Scope · DoD (PR открыт + /tt + кредит автору анкера в описании + журнал/вахта) · не-цели (не трогать соседние PR, не флудить) · эскалация (CLA/Tier-2 → Антон). В сид ВПИСАТЬ: прогнать /outbound-gate перед ship; ⛔ в Google-репо НЕ ставить Co-Authored-By Claude (CLA требует подпись всех авторов).

  6. ЖУРНАЛ + ВАХТА: каждой цели — строка в MEMORY.md (🚀 после ship) + PR в pr_watch; сиды = моя эстафета (Connect): на чекине карта «сиды → чего добились».

ОТЧЁТ Антону (ELI5): какие вендоры взяли и почему (анкер-линк) · кого скипнули и почему · какие сессии посеяны · что на вахте.

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. 25d ago First seen · 32 lines · 313 tokens per session scan A 2bf4847bfb0b

Subscribe to this mod's changes

local-llm-wave is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 313 tokens to every session and 1,216 once invoked, about $0.0013 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.

Building agentsClaude CodeCommitsGit and workflowai-agentsknowledge-managementobsidianpersonal-knowledge-managementsecond-brain
Related

Other skills, from other repositories

gh-issue-triage

An automated workflow for handling issues in a project's GitHub repository, from collecting and analysing them through fixing, testing, and closing them.

Linearl/reasonix_skill_repo · 52 tokens

canvas

Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.

AgriciDaniel/claude-obsidian · 72 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

obsidian-markdown

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.

AgriciDaniel/claude-obsidian · 68 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