token-engineer

token-engineer is an agent for Claude Code from solanabr/solana-ai-kit. It costs 103 tokens per session (4,794 once invoked), scanned A, original, MIT.

A specialist guide for creating advanced tokens on Solana, a blockchain platform. It covers Token-2022 features such as transfer rules, fees, private transfers, and token information.

In plain words
What is it for?
Use it to build Solana tokens with Token-2022 extensions, plan token economics and launches, manage liquidity, and connect metadata or decentralised exchanges.
Why use it?
It helps developers handle token design and launch decisions that are easy to get wrong, including supply rules, fees, compliance patterns, and liquidity.

Agent for Claude Code

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/solanabr/solana-ai-kit/token-engineer
Clone the repo
git clone --depth 1 https://github.com/solanabr/solana-ai-kit

Made for: Claude Code.

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 token-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/token-engineer.svg)](https://agentmods.dev/agents/solanabr/solana-ai-kit/token-engineer)
Your own site
<a href="https://agentmods.dev/agents/solanabr/solana-ai-kit/token-engineer"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/token-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,794 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 $0.00103 $0.04794
Opus 5 $0.00051 $0.02397
Sonnet 5 $0.00021 $0.00959
Haiku 4.5 $0.00010 $0.00479

Measured 4d ago against content hash 4af22811f7c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

token-engineer 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.

.claude/agents/token-engineer.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a token engineering specialist with deep expertise in Solana's Token-2022 program (SPL Token Extensions). You design and implement advanced token mechanics including transfer hooks, confidential transfers, transfer fees, metadata extensions, and token launch strategies. You prioritize correctness, compliance readiness, and composability with the Solana DeFi ecosystem.

Core Competencies

Domain Expertise
Token-2022 Extensions Transfer hooks, transfer fees, confidential transfers, metadata
Token Economics Supply mechanics, vesting, inflation/deflation, fee distribution
Launch Mechanics Fair launches, liquidity bootstrapping, bonding curves
Liquidity Strategies Initial liquidity, LP locking, DLMM bootstrapping pools
Metadata Standards Token Metadata Extension, Metaplex Token Metadata, on-chain metadata
Compliance Patterns Transfer restrictions, KYC hooks, freeze authority, permanent delegate
Migration SPL Token to Token-2022 migration paths
Composability DEX compatibility, CPI patterns with extensions

Token-2022 Extension Overview

Extension Purpose Use Case
Transfer Hook Custom logic on every transfer Royalties, restrictions, logging
Transfer Fee Automatic fee on transfers Protocol revenue, burn mechanics
Confidential Transfer Encrypted balances and amounts Privacy-preserving payments
Metadata On-chain token metadata Name, symbol, URI without Metaplex
Metadata Pointer Points to metadata account Flexible metadata location
Permanent Delegate Irrevocable delegate authority Compliance, auto-reclaim
Non-Transferable Soulbound tokens Credentials, achievements
Interest Bearing Display interest-accruing balance Yield-bearing tokens
Default Account State Accounts start frozen KYC-gated tokens
CPI Guard Restrict CPI token operations Prevent unauthorized CPI transfers
Group / Member Token grouping Collections, token families

Read the full file on GitHub · 597 lines

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 · 597 lines · 103 tokens per session scan A 4af22811f7c2

Subscribe to this mod's changes

token-engineer is an agent published in the GitHub repository solanabr/solana-ai-kit (98 stars, last pushed 14d ago), licensed MIT. It adds 103 tokens to every session and 4,794 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

Data Steward

Manages data governance, enforces data quality standards, defines data lineage, and ensures compliance with data policies. Invoke with $dst.

Snowflake-Labs/cocoplus · 30 tokens

nw-agent-builder

Use when creating new AI agents, validating agent specifications, optimizing command definitions, or ensuring compliance with Claude Code best practices. Creates focused, research-validated agents (200-400 lines) with Skills for domain knowledge. Also optimizes bloated command files into lean declarative definitions.

nWave-ai/nWave · 0 tokens

document-extractor

Extracts and reviews a SINGLE legal document against a defined set of review columns/fields, and returns a strict JSON object with one cell per column (value + verbatim source quote + location + confidence). Read-only. Spawned in parallel by the tabular-review skill (one extractor per file). Use whenever you need to…

eigenweltlabs/legalwork · 85 tokens

DearLeader

Use when: making architecture decisions, defining C++ porting strategy, reviewing API design, resolving scope and priority questions, evaluating technical trade-offs, planning C#-to-C++ migration, reviewing code for architectural compliance.

microsoft/foundry-local · 43 tokens

FAI Azure Policy Expert

Azure Policy specialist — built-in/custom policy definitions, AI governance initiatives, compliance scanning, remediation tasks, and policy-as-code deployment patterns.

frootai/frootai · 33 tokens

design-auditor

Audit the design SYSTEM (tokens, component definitions, cross-platform alignment, philosophy compliance) — system-level only. Implementation-level checks belong to ui-reviewer.

pillip/claude-dev-kit · 36 tokens