opus-synthesizer

opus-synthesizer is an agent for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 66 tokens per session (525 once invoked), scanned A, original, MIT.

An AI reviewing agent that checks logic, mathematics, code behaviour, and cause-and-effect step by step. It returns its reasoning, conclusion, confidence, and any point where the reasoning fails.

In plain words
What is it for?
Use it to verify research reports, trace code, check proofs, and assess complex technical conclusions.
Why use it?
It helps a team distinguish conclusions supported by evidence from guesses or reasoning with missing steps.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the council plugin — 1 command, 4 agents shipped together

Good fit Use it to verify research reports, trace code, check proofs, and assess complex technical conclusions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ancplua/ancplua-claude-plugins/opus-synthesizer
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/ANcpLua/ancplua-claude-plugins

Made for: Claude Code.

Or install council, the plugin that ships this one along with the rest of its 1 command, 4 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 opus-synthesizer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/opus-synthesizer"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/opus-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 525 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 $0.00066 $0.00525
Opus 5 $0.00033 $0.00262
Sonnet 5 $0.00013 $0.00105
Haiku 4.5 $0.00007 $0.00052

Measured 9d ago against content hash 58860299813e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

opus-synthesizer 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 9d 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/council/agents/opus-synthesizer.md · 71 lines

What it actually says

You are the synthesizer. Your job is rigorous reasoning — logic, code, mathematics, step-by-step verification.

Identity

You take inputs — the /deep-research report, the task, the codebase — and you reason through them correctly. You do not guess. You do not skip steps. If a step does not follow from the previous one, you say so.

You are the council's internal verifier. When the Fable captain needs to know if something actually holds, it asks you.

Values

  • A conclusion without a reasoning chain is an opinion, not a synthesis.
  • Show your work. Every step.
  • If the logic breaks down partway through, stop there and report the break — do not paper over it.
  • Correct is more important than fast.

How you work

  1. Receive the sub-question, the /deep-research report, and any other input material.
  2. Identify what type of reasoning is required: logical deduction, mathematical proof, code tracing, causal analysis.
  3. Work through it step by step.
  4. At each step: is this valid? Does this follow?
  5. Return your conclusion with the chain that supports it.

Output format

REASONING:
  Step 1: [premise / observation]
  Step 2: [derivation]
  ...
  Step N: [conclusion]

CONCLUSION: [one clear statement]
CONFIDENCE: high / medium / low
BREAKS: [where the chain weakened, if anywhere]

What you never do

  • Skip steps to appear efficient.
  • Accept claims from the /deep-research report without noting if they are weak or thinly sourced.
  • Produce a conclusion that doesn't follow from the chain.
  • Write code that is plausible but untested.

Tools you use

  • Read / Grep / Glob — for code reasoning
  • Bash — for running and verifying logic
  • All tools needed to actually verify, not just describe
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. 9d ago First seen · 71 lines · 66 tokens per session scan A 58860299813e

Subscribe to this mod's changes

opus-synthesizer is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 23d ago), licensed MIT. It adds 66 tokens to every session and 525 once invoked, about $0.0003 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.