templates AGENTS.md

templates AGENTS.md is an instructions file for Codex, OpenCode from solana-foundation/templates. It costs 403 tokens per session, scanned A, original, MIT.

Repository instructions that explain how coding agents should work in the solana-foundation/templates project. They cover project context, commands, editing rules, and checks.

In plain words
What is it for?
Use them when changing templates or related scripts: read the required documentation, keep edits focused, regenerate metadata when needed, and run the project’s install, generation, lint, and formatting commands.
Why use it?
They reduce accidental changes to generated files and clarify how to validate template updates safely.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/solana-foundation/templates/agents-md
Clone the repo
git clone --depth 1 https://github.com/solana-foundation/templates

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for templates AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/solana-foundation/templates/agents-md.svg)](https://agentmods.dev/instructions/solana-foundation/templates/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/solana-foundation/templates/agents-md"><img src="https://agentmods.dev/badge/instructions/solana-foundation/templates/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 403 This file is loaded in full into every session.
When invoked 403 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00403 $0.00403
Opus 5 $0.00201 $0.00201
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00040 $0.00040

Measured 4d ago against content hash 86180ea00481, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

templates 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 4d 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.

AGENTS.md · 37 lines

What it actually says

Agent Instructions

This file gives AI coding agents the minimum context needed to work safely in this repository. It applies to the whole repo.

Start Here

  • Read README.md, CONTRIBUTING.md, and COMMUNITY_TEMPLATE_GUIDE.md before changing template behavior.
  • Use the focused notes in docs/agents/ for repo map, template metadata, validation, and review checks.
  • Keep changes small and local to the affected template or script.
  • Do not overwrite user work or generated files by hand.

Common Commands

  • pnpm install installs root tooling.
  • pnpm generate regenerates template metadata and docs.
  • pnpm lint validates template structure, metadata, Open Graph images, and formatting.
  • pnpm format formats repo files.

Editing Rules

  • Read docs/agents/repository-map.md before assuming current directory layout.
  • Do not manually edit generated files unless you are updating the generator and intentionally checking output.
  • If you change a template package.json, add/remove a template, or change metadata, run pnpm generate.
  • Every template directory listed in root package.json repokit.groups must contain a package.json and og-image.png.
  • Never add secrets, private keys, personal wallet data, local RPC credentials, or real API tokens.
  • Keep .env files out of templates. Use .env.example when configuration is needed, with placeholders for sensitive values and safe defaults for non-sensitive values.
  • For agent, MCP, wallet, or transaction automation templates, document authentication, permissions, and user approval boundaries clearly.

More Detail

  • docs/agents/repository-map.md
  • docs/agents/template-authoring.md
  • docs/agents/template-metadata.md
  • docs/agents/testing-and-ci.md
  • docs/agents/review-checklist.md
  • docs/agents/known-gotchas.md
Changes

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.

  1. 4d ago First seen · 37 lines · 403 tokens per session scan A 86180ea00481

Subscribe to this mod's changes

templates AGENTS.md is an instructions file published in the GitHub repository solana-foundation/templates (106 stars, last pushed yesterday), licensed MIT. It adds 403 tokens to every session, about $0.0020 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.