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/raydium-io/raydium-docs-v1/agents-mdgit clone --depth 1 https://github.com/raydium-io/raydium-docs-v1Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/raydium-io/raydium-docs-v1/agents-md)<a href="https://agentmods.dev/instructions/raydium-io/raydium-docs-v1/agents-md"><img src="https://agentmods.dev/badge/instructions/raydium-io/raydium-docs-v1/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00964 | $0.00964 |
| Opus 5 | $0.00482 | $0.00482 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
raydium-docs-v1 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 5d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation project instructions
About this project
- This is the Raydium documentation set, built on Mintlify.
- Pages are MDX files with YAML frontmatter; navigation lives in
docs.json. - The information architecture, audience model, and chapter map are defined in
ARCHITECTURE.mdx— consult that before authoring any new page. - The English tree at the repo root is the source of truth. Thirteen locales (
zh,zh-Hant,ja,ko,ru,es,de,fr,pt,tr,vi,id,ar) mirror it; locale pages that don't exist on disk are auto-redirected to English by rules generated indocs.json— see "Multi-language hygiene" below. - Run
mint devto preview locally,mint broken-linksto check links.
Terminology
- Prefer CPMM (constant-product market maker) for the new default pool, not "v5" or "raydium-cp-swap" outside of code references.
- AMM v4 is the original constant-product + OpenBook pool — always written with the version suffix.
- CLMM is the concentrated-liquidity program; positions are NFTs, not LP tokens.
- Stable AMM is the StableSwap-style pool program. It is still a current product — the docs cover it as a live integration target. Don't add deprecation banners.
- Farm v6 is the current farm generation; v3/v5 are wind-down only.
- LaunchLab is the bonding-curve launch program; the user-facing brand is "LaunchLab", not "launchpad".
- Perps are powered by Orderly Network (white-label backend); refer to "Raydium Perps" for the product surface and "Orderly" for the underlying venue.
- Use liquidity provider or LP for stakers in pools/farms; trader for swap users.
Style preferences
- Use active voice and second person ("you").
- Keep sentences concise — one idea per sentence.
- Use sentence case for headings.
- Bold for UI elements: Click Settings.
- Code formatting for file names, commands, paths, program IDs, and code references.
- Every code block that targets the SDK or a program ID should pin a version (SDK version, program ID, Solana cluster, last-verified date) per the convention in
ARCHITECTURE.mdx. The current canonical pin is@raydium-io/[email protected]; if you bump it, run a global search to keep every code-demo page in lock-step.
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.
- 5d ago First seen · 56 lines · 964 tokens per session scan A 3c0a5a8c7800
raydium-docs-v1 AGENTS.md is an instructions file published in the GitHub repository raydium-io/raydium-docs-v1 (2 stars, last pushed yesterday), licensed MIT. It adds 964 tokens to every session, about $0.0048 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 2026-08-31.
Other instructions, from other repositories
dexter-mcp AGENTS.md
AGENTS.md instructions for Dexter-DAO/dexter-mcp, covering dexter mcp agents, current mcp architecture (wip), apps sdk build & deploy, build commands and architecture.
core-ai CLAUDE.md
Claude Code instructions for helius-labs/core-ai, covering core ai, compiler-managed sync, mcp server pin, skill versioning and router surface maintenance.
core-ai AGENTS.md
AGENTS.md instructions for helius-labs/core-ai, covering core ai — agent instructions, repository overview, mcp server setup, api key setup and public tool surface.
behavioral-prediction-mcp CLAUDE.md
Instructions for ChainAware/behavioral-prediction-mcp, covering chainaware behavioral prediction mcp, project overview, mcp tools (14 total), batch pipeline and repository structure.
UCAI AGENTS.md
AGENTS.md instructions for nirholas/UCAI, covering ucai development guidelines, project overview, terminal management and contributing.
UCAI copilot-instructions.md
Copilot instructions for nirholas/UCAI, covering ucai and terminal management.