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.
npx agentmods add skills/banodoco/hivemind/skillnpx skills add banodoco/hivemind --skill skillgit clone --depth 1 https://github.com/banodoco/hivemindWhat 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 | $0.00172 | $0.05397 |
| Opus 5 | $0.00086 | $0.02698 |
| Sonnet 5 | $0.00034 | $0.01079 |
| Haiku 4.5 | $0.00017 | $0.00540 |
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*)" \ 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 |
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.
- 2d ago First seen · 392 lines · 172 tokens per session scan A ad582196068d
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…