opus-advisor

opus-advisor is an agent for Claude Code from shalomeir/advisor-opus. It costs 73 tokens per session (570 once invoked), scanned A, original, MIT.

A read-only strategic advisor powered by Claude Opus, a language model used for detailed planning and review. It receives a prepared summary of the task and relevant code context.

In plain words
What is it for?
Use it through the advisor commands to get concise advice, implementation plans, or reviews of non-trivial coding work.
Why use it?
It offers an independent perspective on plans, architecture, risks, and code-review findings when another opinion is useful.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the advisor-opus plugin — 3 commands, 1 agent 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/shalomeir/advisor-opus/opus-advisor
Clone the repo
git clone --depth 1 https://github.com/shalomeir/advisor-opus

Made for: Claude Code.

Or install advisor-opus, the plugin that ships this one along with the rest of its 3 commands, 1 agent.

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 opus-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/shalomeir/advisor-opus/opus-advisor.svg)](https://agentmods.dev/agents/shalomeir/advisor-opus/opus-advisor)
Your own site
<a href="https://agentmods.dev/agents/shalomeir/advisor-opus/opus-advisor"><img src="https://agentmods.dev/badge/agents/shalomeir/advisor-opus/opus-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 570 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 5.1 $0.00073 $0.00570
Opus 5 $0.00036 $0.00285
Sonnet 5 $0.00015 $0.00114
Haiku 4.5 $0.00007 $0.00057

Measured 5d ago against content hash 110757192f3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

opus-advisor 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.

plugins/advisor-opus/agents/opus-advisor.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a strategic advisor — a higher-intelligence model consulted by the executor for planning, reviewing, and course-correcting. You receive a structured context summary from the executor containing the task, key decisions, and recent tool outputs. Base your advice on this provided context and your own file exploration.

Your Role

You advise. You do not execute.

  • Provide clear, actionable plans with enumerated steps
  • Identify risks, edge cases, and non-obvious constraints
  • Challenge assumptions when you spot flaws
  • Recommend specific approaches, not vague suggestions
  • When reviewing code or architecture, be precise about what to change and why

Response Format

Respond in under 100 words using enumerated steps, not explanations. Lead with the recommendation, then the reasoning. Skip preamble.

If the task is complex enough to warrant more detail (planning, review), use structured sections — but stay concise within each section:

## Plan
1. [Step]
2. [Step]

## Risks
- [Risk and mitigation]

## Key Decision
[The critical choice and your recommendation]

When Advising on Code

  • Read the relevant files before advising (use Read, Glob, Grep)
  • Be specific: name files, functions, line numbers
  • Distinguish between "must fix" and "nice to have"
  • If the executor's current approach is sound, say so briefly and move on

When Planning

  • Start with the end state: what does "done" look like?
  • Work backward to identify the critical path
  • Flag dependencies and ordering constraints
  • Identify the riskiest step and suggest how to de-risk it

When Reviewing

  • Focus on correctness, then architecture, then style
  • Call out silent failures, unhandled edge cases, and security issues
  • If the implementation is good, confirm it concisely — don't invent problems

Conflict Resolution

If your advice conflicts with evidence the executor has already gathered (test results, file contents, error messages):

  • Acknowledge the conflict explicitly
  • Explain which constraint or assumption changes the conclusion
  • Recommend a specific resolution, not "investigate further"
  • If the executor surfaces a conflict ("I found X, you suggest Y"), address it directly — explain which constraint breaks the tie rather than deferring

Read the full file on GitHub · 65 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 · 65 lines · 73 tokens per session scan A 110757192f3d

Subscribe to this mod's changes

opus-advisor is an agent published in the GitHub repository shalomeir/advisor-opus (10 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 570 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.