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/grainsocial/grain/agents-mdgit clone --depth 1 https://github.com/grainsocial/grainWhat 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 | $0.02545 | $0.02545 |
| Opus 5 | $0.01273 | $0.01273 |
| Sonnet 5 | $0.00509 | $0.00509 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
grain 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 3d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hatk project
This is an AT Protocol application built with hatk.
Read the project's lexicons in lexicons/ to understand the data model.
Types are generated from lexicons into hatk.generated.ts — never edit this file directly.
Project structure
| Directory | Purpose |
|---|---|
lexicons/ |
AT Protocol lexicon schemas (JSON). Defines collections and XRPC methods |
server/ |
All server-side code: feeds, XRPC handlers, hooks, labels, OG routes, setup scripts |
app/ |
SvelteKit frontend (routes, components, styles) |
seeds/ |
Test data seeding scripts for local development |
test/ |
Test files (vitest). Run with vp test |
public/ |
Static files served at the root |
Key files
hatk.config.ts— project configuration (seedefineConfigfor type info)hatk.generated.ts— auto-generated server types and helpers. Regenerate withhatk generate typeshatk.generated.client.ts— auto-generated client-safe types andcallXrpc. Never importhatk.generated.tsfrom frontend code
The $hatk alias
Server files in server/ import from $hatk:
import { defineFeed, views, type Status } from "$hatk";
SvelteKit routes and components import from $hatk/client:
import { callXrpc, getViewer } from "$hatk/client";
$hatk resolves to hatk.generated.ts and $hatk/client to hatk.generated.client.ts.
The Vite plugin handles this in dev/build. In tests and production, a Node.js module resolve hook handles it.
Commands
Run npx hatk --help for the full list of commands.
Use npx hatk generate to scaffold new feeds, xrpc handlers, labels, and lexicons
rather than creating files manually. These generate files with the correct imports.
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.
- 3d ago First seen · 250 lines · 2,545 tokens per session scan A 352b4caa1c09
grain AGENTS.md is an instructions file published in the GitHub repository grainsocial/grain (51 stars, last pushed 3d ago), licensed MIT. It adds 2,545 tokens to every session, about $0.0127 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
deno CLAUDE.md
Claude Code instructions for denoland/deno, covering deno development guide, git workflow, high level overview, key directories and quick start.
InsForge copilot-instructions.md
Copilot instructions for InsForge/InsForge, covering project overview, architecture, folder structure, libraries and frameworks and backend.
databasement CLAUDE.md
Claude Code instructions for David-Crty/databasement, covering claude.md, project overview, development commands, setup and installation and running the application.
open-bsp-api CLAUDE.md
Claude Code instructions for matiasbattocchia/open-bsp-api, covering claude.md, project overview, local checks must match ci (deno), debugging production edge functions and timestamps.
bread CLAUDE.md
Instructions for tjakoen/bread, covering claude.md — start here, what this is, start here (reading order), this repo is the stack's control plane — run it and non-negotiables (see conventions for the full rules).
mcp-erpnext AGENTS.md
Instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).