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 instructions/banodoco/hivemind/agents-mdgit 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 | $0.01297 | $0.01297 |
| Opus 5 | $0.00648 | $0.00648 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
hivemind AGENTS.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hivemind — Agent Guide
What this pack provides
Hivemind is a shared knowledge corpus with a read path (public PostgREST over
the raw corpus tables — message_feed, external_resources,
distillations) and a locked write path (a Supabase edge function called
contribute). The seven executors in this pack let you search, fetch, refresh
media URLs, and contribute to the corpus from any environment — CLI, Astrid, or
a Claude Code skill.
hivemind.search queries the three raw tables in parallel with per-token
ILIKE predicates and ranks the merge client-side. It deliberately never
queries the unified_feed UNION view for text search — that view's
derived-table scan blows the anon role's 3s statement budget (HTTP 500 /
SQLSTATE 57014) on any multi-word or per-token OR, and a single multi-word
phrase ILIKE returns zero rows (the literal substring never occurs). Use
unified_feed kind-scoped only for single-row fetches via hivemind.get_item.
When to use each executor
| Executor | Use when … |
|---|---|
hivemind.search |
You need to find distillations, resources, or messages by topic or keyword. Per-token matching over raw tables — works for multi-word queries (the old unified_feed phrase search returned zero rows). Filters: --kinds, --sources, --since, --channel/--author (messages only), --thread (thread id); page with --limit/--offset (response has total/has_more). |
hivemind.get_item |
You have a kind + id and want the full untruncated row with citation context. |
hivemind.refresh_media |
You have a Discord message id and need fresh attachment URLs for expired Discord CDN media. |
hivemind.contribute |
You want to submit a new resource or a cited distillation to the corpus. |
hivemind.ingest_article |
You have a URL and want to extract its text and submit it as a resource. |
hivemind.ingest_workflow |
You have a ComfyUI workflow JSON and want to index its models and structure. |
hivemind.ingest_youtube |
You have a YouTube URL and want to extract captions and submit a transcript resource. |
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 · 92 lines · 1,297 tokens per session scan A f87e0382d11f
hivemind AGENTS.md is an instructions file published in the GitHub repository banodoco/hivemind (64 stars, last pushed 12d ago), licensed MIT. It adds 1,297 tokens to every session, about $0.0065 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.