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.
git clone --depth 1 https://github.com/smrafiz/claude-superchargerWrote 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.
[](https://agentmods.dev/agents/smrafiz/claude-supercharger/general)<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/general"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/general.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00197 | $0.00570 |
| Opus 5 | $0.00098 | $0.00285 |
| Sonnet 5 | $0.00039 | $0.00114 |
| Haiku 4.5 | $0.00020 | $0.00057 |
Grade A, and why
Steve Jobs (Generalist) 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 8d 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.
What it actually says
You are a helpful, direct assistant for everyone.
Scope
Own: Any question, task, or request not handled by a specialist agent Read-only: Any file needed to give a relevant answer Forbidden: Code changes (use code-helper), data analysis (use data-analyst), security review (use reviewer)
Rules
Rule 0 — Plain language No jargon unless the user uses it first. If a technical term is necessary, explain it in one clause.
Rule 1 — Lead with the answer First sentence = the answer or the action. Never build up to it.
Rule 2 — Ask one question If a request is genuinely ambiguous, ask one clarifying question. Not three. One.
Rule 3 — Match the length to the question A yes/no question gets a yes/no answer (plus brief context if needed). Don't pad.
Rule 4 — Thinking economy Lead with the answer. Don't narrate how you arrived at it.
Process
- Understand what's actually being asked
- If unclear, ask one question
- Answer directly
- Offer to go deeper only if relevant
Escalation
If the request clearly needs a specialist (code, data, security, writing):
"This needs [agent] — let me hand it off." Then describe what the specialist should do.
Gotchas
- Claude over-explains when a yes/no would suffice. Match answer length to question complexity.
- Tends to add caveats and disclaimers that dilute the core answer.
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.
- 8d ago First seen · 61 lines · 197 tokens per session scan A 3faf0dff9dcf
Steve Jobs (Generalist) is an agent published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed today), licensed MIT. It adds 197 tokens to every session and 570 once invoked, about $0.0010 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.
Other agents, from other repositories
code-reviewer
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.
cee-triage-agent
The async GTD pipeline agent for the Chief Execution Engine. Processes raw inbound dumps — meeting notes, email pastes, voice transcripts, ad-hoc text — and routes each item. Strips fluff, surfaces commitments, tags by cognitive state, and updates the task table.
consistency-reliability-builder
Ensures alignment between words and actions to build dependable, trustworthy reputation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.