aggregator

aggregator is an agent for Claude Code from MadAppGang/magus. It costs 111 tokens per session (775 once invoked), scanned A, original, MIT.

A report-merging agent that combines several reviews of one target into a single report and labels the level of agreement for each finding. It can also combine research findings from multiple iterations.

In plain words
What is it for?
Use it to consolidate review files, calculate a review verdict from given thresholds, or synthesise research across iterations.
Why use it?
It turns separate review results into one report and applies the supplied thresholds consistently when producing a verdict.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dev plugin — 19 skills, 15 commands, 12 agents shipped together

Good fit Use it to consolidate review files, calculate a review verdict from given thresholds, or synthesise research across iterations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/madappgang/magus/aggregator
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/MadAppGang/magus

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 19 skills, 15 commands, 12 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 aggregator

README.md
[![agentmods](https://agentmods.dev/badge/agents/madappgang/magus/aggregator/github.svg)](https://agentmods.dev/agents/madappgang/magus/aggregator)
Your own site
<a href="https://agentmods.dev/agents/madappgang/magus/aggregator"><img src="https://agentmods.dev/badge/agents/madappgang/magus/aggregator/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 aggregator

Your own site · 80×15
<a href="https://agentmods.dev/agents/madappgang/magus/aggregator"><img src="https://agentmods.dev/badge/agents/madappgang/magus/aggregator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 775 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 $0.00111 $0.00775
Opus 5.5 $0.00044 $0.00310
Sonnet 5.5 $0.00022 $0.00155
Haiku 4.5 $0.00011 $0.00077

Measured 3d ago against content hash 55f5a94bd2f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aggregator 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 3d 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/dev/agents/aggregator.md · 66 lines

What it actually says

<given_reports_never_code>
  Read only the paths the prompt names. Never open the files a review talks about,
  never run a capture script, never grep the codebase to check a reviewer. A finding
  you doubt is reported with its consensus level, not dropped and not re-investigated.
</given_reports_never_code>

<no_rules_of_your_own>
  The verdict words and the thresholds are the dispatcher's, quoted on `THRESHOLDS:`.
  Apply those words and nothing else. Never recall a threshold from memory and never
  invent one when the line is missing.
</no_rules_of_your_own>

<input_contract>
  Review consolidation needs all three of `REVIEWS:`, `THRESHOLDS:` and `OUTPUT:`.
  - No `REVIEWS:` and no `SESSION_PATH:` → return BLOCKED naming the missing line.
  - No `OUTPUT:` → write nothing; return the full consolidation in the message with
    Artifact "Not written — no OUTPUT: line".
  - No `THRESHOLDS:` → consolidate, then end the file with
    `VERDICT: none — THRESHOLDS absent from dispatch`. The gate is meant to fail on it.
  Research synthesis needs `SESSION_PATH:`; without it, return BLOCKED.
</input_contract>

</critical_constraints>

<output_contract> Write exactly one file: the OUTPUT: path, or the synthesis or final-report path under SESSION_PATH. For a review consolidation its last line is VERDICT: <word>, bare. Then return the four-section completion message the skill defines: Artifact, Outcome, Obstacles Encountered, Completion Status. The file is the deliverable; the message says where it is and what it concluded. </output_contract>

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. 3d ago Changed · +1 lines 55f5a94bd2f3
  2. 1mo ago First seen · 65 lines · 111 tokens per session scan A 3119aa71b6fe

Subscribe to this mod's changes

aggregator is an agent published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 775 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-15.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

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.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens