What is tronlink-skills AGENTS.md?

Instructions for read-only coding-agent tools that query the TRON blockchain, a network used for TRX and TRC-20 tokens, through public data services.

Use them to check wallet balances and history, inspect tokens and holders, view market data, estimate DEX swap outcomes, plan network resources, or review staking information.

They clarify which wallet, token, market, and network checks are available and make clear that the tools cannot sign transactions or move funds.

tronlink-skills AGENTS.md — Instructions file for Claude Code and Codex by TronLink: Instructions for read-only coding-agent tools that quer

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tronlink/tronlink-skills/agents-md.svg)](https://agentmods.dev/instructions/tronlink/tronlink-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tronlink/tronlink-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/tronlink/tronlink-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 679 This file is loaded in full into every session.

When invoked 679 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.

Model	Per session	Once invoked
Fable 5.1	$0.00679	$0.00679
Opus 5	$0.00340	$0.00340
Sonnet 5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 6d ago against content hash 3e8f7d3cdda0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tronlink-skills 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

tronlink-skills CLAUDE.md — 89% identical, 6 lines differ

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TronLink Wallet Skills

Read-only AI-agent tools for the TRON network: wallet balances, token info & security heuristics, market data, DEX swap quotes, Energy/Bandwidth resource planning, and TRX Stake 2.0 info.

Read-only — no private keys, no signing, no transfers. Every command is a read query against public TRON APIs (TronGrid / TronScan / CoinGecko / Sun.io router). Requires Node.js >= 18.

Running commands

All skills call one CLI. Resolve its path once per session, then use node "$TRON_API":

TRON_API="${CLAUDE_PLUGIN_ROOT:-$HOME/.tronlink-skills}/scripts/tron_api.mjs"
[ -f "$TRON_API" ] || TRON_API="scripts/tron_api.mjs"   # fallback when run inside the repo
node "$TRON_API" --help

Optional environment:

export TRONGRID_API_KEY="..."        # higher rate limits (optional)
export TRON_NETWORK="mainnet"        # or shasta | nile

Skills — when to use which

Skill	Use for
`tron-wallet`	TRX/TRC-20 balances, holdings, tx history, account info, address validation
`tron-token`	Token search, metadata, holders, trending/rankings, heuristic security snapshot
`tron-market`	Prices, OHLC candles, transfers, volume, whale monitoring, network overview
`tron-swap`	DEX swap quote & route (SunSwap V2/V3, Sun.io), tx status
`tron-resource`	Energy & Bandwidth query, estimation, energy price, cost optimization
`tron-staking`	SR list, staking info, APY estimation (Stake 2.0)

Each skill's SKILL.md (under skills/<name>/) lists its exact commands. The CLI exposes 40 commands total (including one-shot wallet-overview/token-overview and a health-check diagnostic) — run node "$TRON_API" --help for the full list.

MCP alternative

A bundled MCP server (scripts/mcp_server.mjs) exposes 39 tron_* tools backed by the same data, for editors/agents that speak the Model Context Protocol over stdio.

Honest capability notes

tron-token security is a heuristic snapshot (verification, holder concentration, holder count) — not a full audit; it does not detect honeypots, mint/pause/blacklist permissions, or proxy upgradeability.
tron-market K-line returns OHLC only (no volume) and interval selects a time-range bucket, not exact candle spacing.
swap-route is currently an alias of swap-quote.
When an upstream API errors or is rate-limited, commands return an explicit { error, status } envelope (they do not fabricate 0/Unknown/empty results). Surface it as "data unavailable" — never report a 0 price/fee/balance as if it were real.

Read the full file on GitHub · 47 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.

6d ago First seen · 47 lines · 679 tokens per session scan A 3e8f7d3cdda0

Subscribe to this mod's changes

tronlink-skills AGENTS.md is an instructions file published in the GitHub repository TronLink/tronlink-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 679 tokens to every session, about $0.0034 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.

Web3 and blockchain

tronlink-skills AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

TronLink Wallet Skills

Running commands

Skills — when to use which

MCP alternative

Honest capability notes

What this file has done since we first saw it

Other instructions, from other repositories

evmole AGENTS.md

experiencer CLAUDE.md

plamen CLAUDE.md

pip-web CLAUDE.md

bitcoin-mcp copilot-instructions.md

kya-hub AGENTS.md