brevix-opus

brevix-opus is an agent for Claude Code from Yash-Koladiya30/brevix. It costs 74 tokens per session (321 once invoked), scanned A, original, MIT.

A high-cost AI agent tier for difficult software work, using Opus 4.7. It handles problems that need careful reasoning across systems, files, or hidden requirements.

In plain words
What is it for?
Use it for service architecture, multi-agent design, large cross-file refactors, complex bugs spanning layers, or incomplete specifications.
Why use it?
It provides a stronger option when simpler AI models may miss subtle bugs or design constraints, though it costs more to run.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the brevix plugin — 3 skills, 6 agents shipped together

Good fit Use it for service architecture, multi-agent design, large cross-file refactors, complex bugs spanning layers, or incomplete specifications.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yash-koladiya30/brevix/brevix-opus
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.

Clone the repo
git clone --depth 1 https://github.com/Yash-Koladiya30/brevix

Made for: Claude Code.

Or install brevix, the plugin that ships this one along with the rest of its 3 skills, 6 agents.

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 brevix-opus

README.md
[![agentmods](https://agentmods.dev/badge/agents/yash-koladiya30/brevix/brevix-opus/github.svg)](https://agentmods.dev/agents/yash-koladiya30/brevix/brevix-opus)
Your own site
<a href="https://agentmods.dev/agents/yash-koladiya30/brevix/brevix-opus"><img src="https://agentmods.dev/badge/agents/yash-koladiya30/brevix/brevix-opus/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 brevix-opus

Your own site · 80×15
<a href="https://agentmods.dev/agents/yash-koladiya30/brevix/brevix-opus"><img src="https://agentmods.dev/badge/agents/yash-koladiya30/brevix/brevix-opus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 321 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 $0.00074 $0.00321
Opus 5 $0.00037 $0.00161
Sonnet 5 $0.00015 $0.00064
Haiku 4.5 $0.00007 $0.00032

Measured 10d ago against content hash 71b9084d02da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

brevix-opus 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.

agents/brevix-opus.md · 36 lines

What it actually says

Brevix Opus Tier

Top tier. Reserve for tasks where weaker models will produce subtly wrong output.

Good fit

  • System / service architecture
  • Multi-agent / orchestration design
  • Cross-cutting refactor that spans many files and modules
  • Hard bugs that span layers (e.g. async race conditions, lock cycles)
  • Design with hidden constraints (legal / compliance / SLA)
  • Synthesizing a spec from incomplete requirements

Wasteful fit (do NOT call)

  • Anything Haiku or Sonnet can handle
  • Mechanical edits, format, rename, summarize
  • Simple Q&A you already know the answer to

Output rule

Lead with the decision, then the reasoning chain that supports it. Cite file:line. Call out tradeoffs explicitly. End with the proposed action and an explicit alternative.

Top tier policy

No further escalation possible. If you cannot answer reliably, return: unresolved: <what is missing> Caller decides next move (more context, human review, or accept the gap).

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 · 36 lines · 74 tokens per session scan A 71b9084d02da

Subscribe to this mod's changes

brevix-opus is an agent published in the GitHub repository Yash-Koladiya30/brevix (4 stars, last pushed 22d ago), licensed MIT. It adds 74 tokens to every session and 321 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.