template-authoring

template-authoring is an agent for coding agents from solana-foundation/templates. It costs 0 tokens per session (375 once invoked), scanned A, original, MIT.

An agent for adding or changing project templates, including their required files and listing information.

In plain words
What is it for?
Use it to create or edit community templates, check their package metadata, and regenerate project metadata after changes.
Why use it?
It helps keep templates in the expected directory structure and prevents missing metadata or committed secrets.

Agent

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 agents/solana-foundation/templates/template-authoring
Clone the repo
git clone --depth 1 https://github.com/solana-foundation/templates

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 template-authoring

README.md
[![agentmods](https://agentmods.dev/badge/agents/solana-foundation/templates/template-authoring.svg)](https://agentmods.dev/agents/solana-foundation/templates/template-authoring)
Your own site
<a href="https://agentmods.dev/agents/solana-foundation/templates/template-authoring"><img src="https://agentmods.dev/badge/agents/solana-foundation/templates/template-authoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00375
Opus 5 $0.00000 $0.00187
Sonnet 5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00038

Measured 4d ago against content hash 62601fe42c75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

template-authoring 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.

docs/agents/template-authoring.md · 52 lines

What it actually says

Template Authoring

Use this when adding or changing a template.

Required Files

Each template directory scanned by repokit.groups must include:

  • package.json
  • og-image.png

Community templates belong under community/<template-name>/ unless a maintainer asks for another root.

Package Metadata

Template package.json files should include these listing fields:

  • name
  • displayName
  • description
  • usecase
  • keywords

Follow existing templates for conventions. Keep descriptions concise because they are shown in listings.

The generator and linter currently enforce name, description, and non-empty keywords. The contributor guide also expects displayName and usecase for complete template listings.

Configuration And Secrets

  • Do not commit .env files, private keys, seed phrases, API tokens, or personal wallet addresses.
  • Use .env.example for required configuration.
  • Use placeholders for sensitive values; safe defaults such as SOLANA_CLUSTER=devnet are okay.
  • Avoid dependencies or setup scripts that require hidden local state.

Generated Metadata

Run pnpm generate after adding, removing, renaming, or changing metadata for a template.

Do not manually patch templates.json, TEMPLATES.md, or .github/workflows/templates.json unless the generator itself is being changed and you are checking expected output.

Agent And MCP Templates

Templates that expose agent, MCP, wallet, signing, or transaction automation behavior need clear README notes for:

  • What the agent can access.
  • What authentication is required.
  • Which actions require explicit user approval.
  • Whether the template can sign messages, submit transactions, trade, or move funds.
  • How users revoke access.

Avoid unsafe defaults. Wallet or transaction automation should not run without a deliberate user action.

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 · 52 lines · 0 tokens per session scan A 62601fe42c75

Subscribe to this mod's changes

template-authoring is an agent published in the GitHub repository solana-foundation/templates (106 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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.