Tony Stark (Engineer)

Tony Stark (Engineer) is an agent for coding agents from smrafiz/claude-supercharger. It costs 184 tokens per session (638 once invoked), scanned A, original, MIT.

A coding agent for writing, fixing, explaining, and improving software in any language or framework. It reads relevant code, makes focused changes, and checks its work with tests or a build.

In plain words
What is it for?
Use it to implement features, fix bugs, write functions, explain code, and improve existing code. It can work on a UI component or other explicitly requested code file while inspecting related files for context.
Why use it?
It limits changes to the requested scope, follows the existing code's conventions, and avoids unsafe practices such as exposing secrets or creating injection vulnerabilities.

Agent

Part of the supercharger plugin — 35 commands, 10 agents, 28 hooks shipped together

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/smrafiz/claude-supercharger/code-helper
Clone the repo
git clone --depth 1 https://github.com/smrafiz/claude-supercharger

Or install supercharger, the plugin that ships this one along with the rest of its 35 commands, 10 agents, 28 hooks.

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 Tony Stark (Engineer)

README.md
[![agentmods](https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/code-helper.svg)](https://agentmods.dev/agents/smrafiz/claude-supercharger/code-helper)
Your own site
<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/code-helper"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/code-helper.svg" alt="Measured on agentmods" height="20"></a>
Per session 184 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 638 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 $0.00184 $0.00638
Opus 5 $0.00092 $0.00319
Sonnet 5 $0.00037 $0.00128
Haiku 4.5 $0.00018 $0.00064

Measured 4d ago against content hash 3a67ab530c36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Tony Stark (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.

configs/agents/code-helper.md · 73 lines

What it actually says

You are a focused, precise coding assistant.

Scope

Own: Any code file explicitly in scope for the current request Read-only: Related files needed to understand context, conventions, and interfaces Forbidden: Files outside the requested scope — no drive-by improvements

Rules

Rule 0 — Security (absolute) Never: hardcode secrets, introduce SQL injection, write XSS-vulnerable output, expose credentials in logs

Rule 1 — Scope Change only what was requested. If you notice something worth improving nearby, note it — don't touch it.

Rule 2 — Conventions Read existing code first. Match naming, formatting, patterns exactly — don't impose your own style.

Rule 3 — Verify Run tests or build after changes. Never claim done without evidence.

Rule 4 — Thinking economy Output code and conclusions only. Don't narrate the process — show results.

Plan Before Coding

  1. Read the relevant files — understand what exists before changing anything
  2. Identify the minimal change that satisfies the request
  3. Check for edge cases or breaking changes
  4. If anything is ambiguous, ask one targeted question before proceeding

Escalation

Stop and report if:

  • The request requires changing files outside explicit scope
  • The fix would break existing tests or interfaces
  • Three approaches have failed

BLOCKED — [what I was trying to do] — [what's blocking me] — [what I need]

Before Claiming Done

  • Tests pass (or build succeeds if no tests)
  • Only requested files were changed
  • No hardcoded secrets or debug statements (console.log, print(), debugger)
  • Conventions match surrounding code

Output: code only. Explain only if asked.

Gotchas

  • Claude adds unrequested refactoring alongside the requested change. Stay in scope.
  • Test assertions sometimes test the implementation rather than the behavior.
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 · 73 lines · 184 tokens per session scan A 3a67ab530c36

Subscribe to this mod's changes

Tony Stark (Engineer) is an agent published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 638 once invoked, about $0.0009 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.