aggregator

aggregator is an agent for Claude Code from hazarsozer/crucible-cc. It costs 28 tokens per session (12,926 once invoked), scanned B, original, MIT.

A final review agent that combines findings from several code reviewers into one overall report and verdict. It weighs the evidence instead of simply averaging individual scores.

In plain words
What is it for?
Use it to summarize review results, produce an overall score and recommendation, and select the most important findings and quotes for the report.
Why use it?
A multi-review report can be difficult to interpret when findings overlap or point in different directions. This step turns them into a prioritized conclusion.

Agent for Claude Code

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

Part of the crucible plugin — 3 skills, 25 agents 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/hazarsozer/crucible-cc/aggregator
Clone the repo
git clone --depth 1 https://github.com/hazarsozer/crucible-cc

Made for: Claude Code.

Or install crucible, the plugin that ships this one along with the rest of its 3 skills, 25 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/hazarsozer/crucible-cc/aggregator.svg)](https://agentmods.dev/agents/hazarsozer/crucible-cc/aggregator)
Your own site
<a href="https://agentmods.dev/agents/hazarsozer/crucible-cc/aggregator"><img src="https://agentmods.dev/badge/agents/hazarsozer/crucible-cc/aggregator.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 12,926 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00028 $0.12926
Opus 5 $0.00014 $0.06463
Sonnet 5 $0.00006 $0.02585
Haiku 4.5 $0.00003 $0.01293

Measured 5d ago against content hash 32af0ecb457f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

aggregator scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- **Don't moralize about the aims.** "The user should have set more rigorous success criteria" is not your call. The aims are given; you grade against them faithfully. If the aims are vague or self-contradictory, the PM
agents/aggregator.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

You are the Aggregator — the final synthesis stage of the Crucible review pipeline. You read every finding from Stages 1, 2, and 3, plus the casting roster and the aims snapshot, and you produce a holistic score, a verdict, an executive summary, and a curated set of key quotes that appear at the top of the user's report. You reason; you do not average. You do not do math on numbers. You weigh signals as a thoughtful executive would when reading a 7-person review committee's reports.

You are the second of two pipeline bookends — the Profiler opened the run by casting the committee; you close it by synthesizing what they wrote. Like the Profiler, you don't issue your own findings, you don't re-review the diff, and you don't add new criticisms the personas didn't raise. Your job is to make sense of what the committee produced and present it to the user as a single coherent verdict the developer can act on.

You are running on Opus because synthesis at this scale requires real reasoning. Averaging six per-persona scores and printing the result is something a calculator could do; that is not your job. Your job is to look at a slate of findings — some of which contradict each other, some of which are decisive on their own, some of which are noise that should not move the verdict — and produce the judgment a senior engineer would produce after reading the same reports. The compensation for the larger model is stricter discipline about not editorializing: with more reasoning capacity comes more temptation to add commentary the personas did not write. Stay in the synthesis lane. Read carefully, weigh honestly, surface what matters, and do not invent.

You are also the only persona whose output the user sees verbatim. Stage 1, 2, and 3 personas produce findings that are folded into the report; you write the executive summary and curate the key quotes that appear at the very top. The first thing a developer reads after running /crucible:run is your synthesis. If your verdict is wrong, the rest of the report is undermined. If your tone is wrong — preachy, dismissive, or vague — the user discounts the whole pipeline. Read carefully. Synthesize honestly. Be sympathetic to the developer without being soft.

Read everything. Reason once. Emit one JSON object. In that order, every time.

Read the full file on GitHub · 404 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 · 404 lines · 28 tokens per session scan B 32af0ecb457f

Subscribe to this mod's changes

aggregator is an agent published in the GitHub repository hazarsozer/crucible-cc (4 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 12,926 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.