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/synthetic-sciences/openscience/agents-mdgit clone --depth 1 https://github.com/synthetic-sciences/openscienceWhat 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 | $0.00452 | $0.00452 |
| Opus 5 | $0.00226 | $0.00226 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
openscience 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.
What it actually says
- To regenerate the JavaScript SDK, run
./tooling/repo/generate.tsfrom the repo root. - ALWAYS USE PARALLEL TOOLS WHEN APPLICABLE.
- The default branch in this repo is
main. - Prefer automation: execute requested actions without confirmation unless blocked by missing info or safety/irreversibility.
Style Guide
- Keep things in one function unless composable or reusable
- Avoid unnecessary destructuring. Instead of
const { a, b } = obj, useobj.aandobj.bto preserve context - Avoid
try/catchwhere possible - Avoid using the
anytype - Prefer single word variable names where possible
- Use Bun APIs when possible, like
Bun.file() - Rely on type inference when possible; avoid explicit type annotations or interfaces unless necessary for exports or clarity
Avoid let statements
We don't like let statements, especially combined with if/else statements.
Prefer const.
Good:
const foo = condition ? 1 : 2
Bad:
let foo
if (condition) foo = 1
else foo = 2
Avoid else statements
Prefer early returns or using an iife to avoid else statements.
Good:
function foo() {
if (condition) return 1
return 2
}
Bad:
function foo() {
if (condition) return 1
else return 2
}
Prefer single word naming
Try your best to find a single word name for your variables, functions, etc. Only use multiple words if you cannot.
Good:
const foo = 1
const bar = 2
const baz = 3
Bad:
const fooBar = 1
const barBaz = 2
const bazFoo = 3
Testing
You MUST avoid using mocks as much as possible.
Tests MUST test actual implementation, do not duplicate logic into a test.
Run the suite with bun test from backend/cli.
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 · 85 lines · 452 tokens per session scan A f33631907295
openscience AGENTS.md is an instructions file published in the GitHub repository synthetic-sciences/openscience (3,362 stars, last pushed 2d ago), licensed Apache-2.0. It adds 452 tokens to every session, about $0.0023 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
zeroclaw AGENTS.md
Instructions for zeroclaw-labs/zeroclaw, covering agents.md - zeroclaw, single source of truth, safety and privacy, working rules and user-facing text.
zeroclaw CLAUDE.md
Instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
terminator CLAUDE.md
Instructions for mediar-ai/terminator, covering terminator - ai-native gui automation, installation, release, or with globally installed cli and development.
ralphy CLAUDE.md
Claude Code instructions for alecs5am/ralphy, a project described as: 🎬 Give AI agents tools to create viral videos. Influence at scale, from your terminal.
Ornn CLAUDE.md
Instructions for ChronoAIProject/Ornn, covering claude.md — chrono-ornn, product positioning, tech stack, architecture and code standards.