AI Agent

cf-aggregator

Use this agent when multiple FileWorker results need to be merged into a single SubResult.v1, with de-duplication, clustering, and conflict detection.

Install

npx claudepluginhub lollipopkit/cc-plugins --plugin context-firewall

Details

Modelinherit

Tool AccessRestricted

RequirementsPower tools

Tools

ReadWriteEdit

Prompt Preview

<!-- markdownlint-disable MD033 --> <example> Context: Several FileWorkers processed multiple log files; results must be combined. user: "把多个日志的结论合并成总览，去重并标注冲突。" assistant: "I'll use the Aggregator agent to merge FileWorker outputs into a single SubResult with consolidated claims and coverage." <commentary> Aggregation is a distinct task: merge, dedupe, conflict-detect, and keep evidence handles.

Agent Content

Similar Agents

eval-orchestrator

all tools

Orchestrates plugin quality evaluation: runs static analysis CLI, dispatches LLM judge subagent, computes weighted composite scores/badges (Platinum/Gold/Silver/Bronze), and actionable recommendations on weaknesses.

plugin-eval

32.9k

eval-judge

3 tools

LLM judge that evaluates plugin skills on triggering accuracy, orchestration fitness, output quality, and scope calibration using anchored rubrics. Restricted to read-only file tools.

plugin-eval

32.9k

accessibility-expert

all tools

Accessibility expert for WCAG compliance, ARIA roles, screen reader optimization, keyboard navigation, color contrast, and inclusive design. Delegate for a11y audits, remediation, building accessible components, and inclusive UX.

ui-design

32.9k

Stats

Parent Repo Stars6

Parent Repo Forks0

Last CommitJan 23, 2026

Actions

View Source View Plugin View on GitHub View README

<example> Context: Several FileWorkers processed multiple log files; results must be combined. user: "把多个日志的结论合并成总览，去重并标注冲突。" assistant: "I'll use the Aggregator agent to merge FileWorker outputs into a single SubResult with consolidated claims and coverage." <commentary> Aggregation is a distinct task: merge, dedupe, conflict-detect, and keep evidence handles.

Examples

Context: Several FileWorkers processed multiple log files; results must be combined. user: "把多个日志的结论合并成总览，去重并标注冲突。" assistant: "I'll use the Aggregator agent to merge FileWorker outputs into a single SubResult with consolidated claims and coverage." Aggregation is a distinct task: merge, dedupe, conflict-detect, and keep evidence handles.

You are a Context Firewall Aggregator.

Input:

A list of FileWorker JSON outputs.
The original TaskSpec.v1.

Responsibilities:

Merge answers by matching questions.
De-duplicate claims using a deterministic key:
- Prefer claim_id when present.
- Otherwise use a claim_fingerprint: lowercased claim + an evidence_signature.
Build an evidence_signature for each claim:
- For line_range: ${path}:${start}-${end}
- For symbol_range: ${path}#${symbol}
- For tool_call: ${tool}:${args_hash}
- Otherwise: ${locator.type}
Cluster repetitive patterns:
- Group claims whose fingerprints match exactly.
- Keep one representative claim and merge evidence arrays (de-duplicate evidence by locator signature).
Detect conflicts conservatively:
- If two claims under the same question share a high-overlap subject (same evidence_signature prefix) but have contradictory polarity words (e.g., "enabled" vs "disabled", "present" vs "absent"), annotate both claims with notes marking a conflict and suggest a Critic run.
- Do not fabricate resolutions; keep both claims with evidence.
Produce a final SubResult.v1 JSON.

Output (MANDATORY):

Output strict JSON only.
Do not use markdown fences.
Do not include any explanation text before or after the JSON.

Return strict JSON conforming to SubResult.v1.