premium-reasoner

premium-reasoner is an agent for Claude Code from jeroromano/claude-code-orchestration-template. It costs 78 tokens per session (661 once invoked), scanned A, original, MIT.

A high-cost AI reasoning agent reserved for difficult or important questions. It only runs when the delegation request includes an explicit approval token and reports that a premium model was used.

In plain words
What is it for?
Use it for a specific high-stakes or unusually difficult question after a human has approved premium spending, especially when a less expensive reasoning agent was not enough.
Why use it?
It prevents accidental use of an expensive model for routine work and makes the cost and model source visible. The approval check also stops the agent before it reads files or analyzes anything when permission is missing.

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/jeroromano/claude-code-orchestration-template/premium-reasoner
Clone the repo
git clone --depth 1 https://github.com/jeroromano/claude-code-orchestration-template

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 premium-reasoner

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeroromano/claude-code-orchestration-template/premium-reasoner.svg)](https://agentmods.dev/agents/jeroromano/claude-code-orchestration-template/premium-reasoner)
Your own site
<a href="https://agentmods.dev/agents/jeroromano/claude-code-orchestration-template/premium-reasoner"><img src="https://agentmods.dev/badge/agents/jeroromano/claude-code-orchestration-template/premium-reasoner.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 661 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 $0.00078 $0.00661
Opus 5 $0.00039 $0.00331
Sonnet 5 $0.00016 $0.00132
Haiku 4.5 $0.00008 $0.00066

Measured 5d ago against content hash b9d7e1c6a084, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

premium-reasoner 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 5d 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/premium-reasoner.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the most expensive reasoning slot in this repo. Act like it.

Gate - run before any analysis

  1. If the delegation prompt does not contain the literal token PREMIUM-APPROVED, stop immediately and return exactly one line: "Not run: premium-reasoner requires explicit human authorization (PREMIUM-APPROVED missing)." Do not read files. Do not analyze.
  2. Open every report with one line: "Cost notice: premium-tier invocation - verify which pool it drew from (plan quota / usage credits / API billing) with /usage." This template hardcodes no rates, caps or dates because billing regimes change; the human verifies the current one. Immediately below the cost notice, add the provenance line: Ran as: premium-reasoner on <model name and ID exactly as your runtime context states them; if no such statement exists, write "model not reported by harness">; effort: pinned high (frontmatter - update this line if you change the pin). Quote the context statement verbatim - never answer from self-belief. Maintenance note: in a private fork with a stable, known billing regime you may replace this generic notice with a specific one. Step 1 is the permanent control; this step is disclosure only.

Model configuration - the one line to edit

model: fable pins Anthropic's current top tier as a functional default. No access to it? Point model: at your highest available tier (for example opus), or delete this agent entirely - the routing table degrades cleanly without it. After any change, verify in /agents that the value resolved: models excluded by an organization allowlist are silently skipped and the subagent runs on the inherited model instead. If you rename this agent or its token, run git grep -l PREMIUM-APPROVED and update every file it returns in the same commit: a partial rename leaves the gate failing closed forever (safe, but broken).

Contract

Same as deep-reasoner: stateless, read-only, one scoped question in, one decision-grade analysis out. If critical context is missing from the prompt, name what is missing and stop - do not explore speculatively at this price.

Read the full file on GitHub · 31 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. 5d ago First seen · 31 lines · 78 tokens per session scan A b9d7e1c6a084

Subscribe to this mod's changes

premium-reasoner is an agent published in the GitHub repository jeroromano/claude-code-orchestration-template (1 stars, last pushed 26d ago), licensed MIT. It adds 78 tokens to every session and 661 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.

Related

Other agents, from other repositories

check

Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.

mindfold-ai/Trellis · 34 tokens

vc-plan-agent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens

vc-ui-ux-designer

Use this agent when the user needs UI/UX execution support including interface implementation, design-system polish, responsive layouts, animations, accessibility review, or design documentation. Examples:\n\n \nContext: User wants to implement a new landing page from an approved direction\nuser: "I need a modern…

withkynam/vibecode-pro-max-kit · 428 tokens

architecture-reviewer

Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.

FlorianBruniaux/claude-code-plugins · 45 tokens

planner

Strategic planning agent — read-only exploration before implementation. Use to decompose tasks, analyze codebases, and produce a detailed plan. Never modifies files.

FlorianBruniaux/claude-code-plugins · 33 tokens