resistance-tools-skill

resistance-tools-skill is a skill for Claude Code, Codex from TONresistor/resistance-tools-mcp. It costs 75 tokens per session (1,521 once invoked), scanned A, original, MIT.

A toolset for operating TON blockchain services, including TON Sites, TON DNS, storage, wallets, permissions, and paid providers. TON is a blockchain network and its related services.

In plain words
What is it for?
Managing TON sites, domains, subdomains, storage, wallet access, permissions, audits, paid services, and manually confirmed transactions.
Why use it?
It helps an agent choose and sequence the right operations, check the resulting state, and recover from tool errors while keeping sensitive actions controlled.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Part of the resistance-tools-mcp plugin — 1 skill, 1 MCP server shipped together

Good fit Managing TON sites, domains, subdomains, storage, wallet access, permissions, audits, paid services, and manually confirmed transactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tonresistor/resistance-tools-mcp/resistance-tools-skill
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.

Any agent
npx skills add TONresistor/resistance-tools-mcp --skill resistance-tools-skill
Clone the repo
git clone --depth 1 https://github.com/TONresistor/resistance-tools-mcp

Made for: Claude Code, Codex.

Or install resistance-tools-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 resistance-tools-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/tonresistor/resistance-tools-mcp/resistance-tools-skill/github.svg)](https://agentmods.dev/skills/tonresistor/resistance-tools-mcp/resistance-tools-skill)
Your own site
<a href="https://agentmods.dev/skills/tonresistor/resistance-tools-mcp/resistance-tools-skill"><img src="https://agentmods.dev/badge/skills/tonresistor/resistance-tools-mcp/resistance-tools-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for resistance-tools-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/tonresistor/resistance-tools-mcp/resistance-tools-skill"><img src="https://agentmods.dev/badge/skills/tonresistor/resistance-tools-mcp/resistance-tools-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,521 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00075 $0.01521
Opus 5 $0.00037 $0.00760
Sonnet 5 $0.00015 $0.00304
Haiku 4.5 $0.00007 $0.00152

Measured 10d ago against content hash bc8d65de5d5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

resistance-tools-skill 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 10d 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.

skills/resistance-tools-skill/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resistance Tools

Use the hosted resistance-tools-mcp MCP and treat its runtime tool schema and structured results as canonical. Complete the requested workflow, verify the resulting state, and give the user the useful outcome instead of raw tool output.

Connection and permissions

Keep these identifiers distinct:

  • Marketplace/source: resistance-tools
  • Plugin and MCP server: resistance-tools-mcp
  • Skill: resistance-tools-skill

For a fresh Codex plugin install:

codex plugin marketplace add TONresistor/resistance-tools-mcp@main
codex plugin add resistance-tools-mcp@resistance-tools
codex mcp login resistance-tools-mcp

For a fresh Claude Code plugin install:

claude plugin marketplace add TONresistor/resistance-tools-mcp@main
claude plugin install resistance-tools-mcp@resistance-tools
claude mcp login resistance-tools-mcp

For MCP-only setup:

Codex:

codex mcp add resistance-tools-mcp --url https://app.resistance.dog/api/mcp
codex mcp login resistance-tools-mcp

Claude Code:

claude mcp add --transport http resistance-tools-mcp https://app.resistance.dog/api/mcp
claude mcp login resistance-tools-mcp

If the MCP is already registered, do not add it again. Let the user select permissions or use Approve all on the approval page; never choose permissions for them. Never request a seed phrase, private key, proof, signature, bearer token, or wallet export.

For a normal update from version 0.2.3 or later, preserve the current marketplace identity and use the matching sequence.

Codex:

codex plugin marketplace upgrade resistance-tools
codex plugin remove resistance-tools-mcp@resistance-tools
codex plugin add resistance-tools-mcp@resistance-tools

Claude Code:

claude plugin marketplace update resistance-tools
claude plugin update resistance-tools-mcp@resistance-tools

Use the configured MCP name, not an OAuth error code, to detect the retired alias. If the configured name is resistance-tools, give the matching cleanup and reinstall sequence below; if an old entry is already absent, continue. If it is already resistance-tools-mcp, preserve the installation. A normal access-token expiry refreshes automatically. invalid_target alone does not prove an alias problem. On an auth failure, load references/wallet.md; never reinstall or re-login from that error alone.

Read the full file on GitHub · 135 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 135 lines · 75 tokens per session scan A bc8d65de5d5f

Subscribe to this mod's changes

resistance-tools-skill is a skill published in the GitHub repository TONresistor/resistance-tools-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,521 once invoked, about $0.0004 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.