hivemind

A read-only search service for the Banodoco community knowledge base, which collects discussions, resources, workflows, and researched answers about AI-generated images and videos.

In plain words
What is it for?
Use it to look up workflows and troubleshooting for tools and models such as Wan, ComfyUI, VACE, LTX, and related image- and video-generation systems.
Why use it?
It provides community techniques, settings, comparisons, and known problems that may not appear in official tool documentation.

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/banodoco/hivemind/skill
Any agent
npx skills add banodoco/hivemind --skill skill
Clone the repo
git clone --depth 1 https://github.com/banodoco/hivemind

Made for: Claude Code, Codex.

Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,397 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00172 $0.05397
Opus 5 $0.00086 $0.02698
Sonnet 5 $0.00034 $0.01079
Haiku 4.5 $0.00017 $0.00540

Measured 2d ago against content hash ad582196068d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hivemind scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://ujlwuvkrxlvoswwkerdf.supabase.co/rest/v1/message_feed?select=message_id,content,author_name,channel_name,created_at&limit=5&order=created_at.desc&or=(content.ilike.*wan*,content.ilike.*animate*)" \
skill/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hivemind

A read-only public endpoint exposing the Banodoco knowledge corpus — community knowledge about video/image generation you can't get from official docs: workflow tips, model comparisons, settings tweaks, gotchas, and links to Kijai/Ablejones/community workflows. It layers three things into one searchable feed: messages (raw Discord), resources (articles, transcripts, workflows), and distillations (curated Q&A with cited sources). Distillations make the corpus self-improving — every researched answer you submit becomes permanently searchable.

Quick start

Endpoint: https://ujlwuvkrxlvoswwkerdf.supabase.co/rest/v1
Key (anon publishable, safe to commit):
  apikey: sb_publishable_O38oPBafrBoFrpi_rlWJvA_UJrulFsx

Smoke test (raw search surface — per-token OR on message content; do NOT text-search unified_feed, the UNION scan times out with 57014):

curl -s "https://ujlwuvkrxlvoswwkerdf.supabase.co/rest/v1/message_feed?select=message_id,content,author_name,channel_name,created_at&limit=5&order=created_at.desc&or=(content.ilike.*wan*,content.ilike.*animate*)" \
  -H "apikey: sb_publishable_O38oPBafrBoFrpi_rlWJvA_UJrulFsx"

Surfaces at a glance — pick by what you want

You want to… Use Why
Search curated Q&A (distillations) distillations + or=(question.ilike.*T*,answer.ilike.*T*,conditions.ilike.*T*) flywheel, highest signal; status pending,approved
Search resources (workflows, articles) external_resources?kind=eq.<resource-kind>&or=(title.ilike.*T*) raw table, kind btree + trigram GIN
Search message content (free text) message_feed + or=(content.ilike.*T1*,content.ilike.*T2*) per-token OR is index-friendly; unified_feed ilike times out (57014)
Just search everything at once python3 executors/search/run.py --query "wan animate workflow" the pack executor: 3 scopes in parallel, per-token predicates, client-ranked merge
Search one Discord channel python3 executors/search/run.py --query "lora" --channel wan_chatter channel-scoped message search
Search one person's messages python3 executors/search/run.py --query "lora" --author Kijai author-scoped message search
Search inside a thread python3 executors/search/run.py --query "context" --thread <snowflake> index-backed message_filters thread surface
Page through results --limit 10 --offset 10 (response has total/has_more) deterministic ranked pool; stable pages
Filter messages by a field (pinned, thread, reply, attachment, channel) message_filters index-backed, ~0.1–0.25s
Fetch a full row by id get_item (executor) or unified_feed?item_id=eq.<id> complete body + metadata + cites
Refresh an expiring media URL refresh-media-urls edge function fresh Discord CDN URL

Read the full file on GitHub · 392 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. 2d ago First seen · 392 lines · 172 tokens per session scan A ad582196068d

Subscribe to this mod's changes

hivemind is a skill published in the GitHub repository banodoco/hivemind (64 stars, last pushed 12d ago), licensed MIT. It adds 172 tokens to every session and 5,397 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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