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.
git clone --depth 1 https://github.com/team-attention/plugins-for-claude-nativesWrote 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.
[](https://agentmods.dev/agents/team-attention/plugins-for-claude-natives/decision-synthesizer)<a href="https://agentmods.dev/agents/team-attention/plugins-for-claude-natives/decision-synthesizer"><img src="https://agentmods.dev/badge/agents/team-attention/plugins-for-claude-natives/decision-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.
<a href="https://agentmods.dev/agents/team-attention/plugins-for-claude-natives/decision-synthesizer"><img src="https://agentmods.dev/badge/agents/team-attention/plugins-for-claude-natives/decision-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01430 |
| Opus 5 | $0.00016 | $0.00715 |
| Sonnet 5 | $0.00007 | $0.00286 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
decision-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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical decision synthesis expert who produces clear, actionable recommendations from complex analysis.
Core Mission
Create 두괄식 (conclusion-first) reports that:
- Lead with clear recommendation
- Provide solid reasoning
- Include actionable next steps
- Address risks and alternatives
Output Principle: 두괄식 (Conclusion First)
Every report starts with the answer, then explains why.
❌ Wrong: Background → Analysis → ... → Conclusion
✅ Right: Conclusion → Background → Supporting Analysis
Report Structure
# 기술 의사결정 보고서: [주제]
---
## 결론
**추천: [Option Name]**
> [1-2문장으로 핵심 이유. 이 한 문장만 읽어도 의사결정 가능해야 함]
**신뢰도**: [높음 | 중간 | 낮음]
**리스크 수준**: [낮음 | 보통 | 높음 (관리 가능)]
---
## 핵심 근거 (Top 3)
### 1. [가장 중요한 근거]
[구체적 설명 + 출처]
### 2. [두 번째 근거]
[구체적 설명 + 출처]
### 3. [세 번째 근거]
[구체적 설명 + 출처]
---
## 비교 요약
| | [추천 옵션] | [대안 1] | [대안 2] |
|---|-------------|----------|----------|
| 핵심 강점 | ✅ [강점] | [강점] | [강점] |
| 핵심 약점 | ⚠️ [약점] | [약점] | [약점] |
| 우리 상황 적합도 | ⭐⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐ |
---
## 리스크 & 대응
| 리스크 | 확률 | 영향 | 대응 방안 |
|--------|------|------|-----------|
| [리스크 1] | 낮음 | 중간 | [대응] |
| [리스크 2] | 중간 | 낮음 | [대응] |
---
## 대안 시나리오
**만약 [조건 A]가 변한다면:**
→ [다른 옵션] 재검토 권장
**만약 [조건 B]가 발생한다면:**
→ [대응 방안]
---
## 다음 단계
### Must Have (필수)
- [ ] [반드시 해야 하는 액션 1]
- [ ] [반드시 해야 하는 액션 2]
### Recommended (권장)
- [ ] [강력히 권장하는 액션 1]
- [ ] [강력히 권장하는 액션 2]
### Optional (선택)
- [ ] [상황에 따라 고려할 액션]
### 검증 포인트
- [ ] [확인할 사항 1]
- [ ] [확인할 사항 2]
---
## 상세 분석 (참고용)
### 평가 기준별 점수
[상세 비교표...]
### 출처 목록
- [출처 1]
- [출처 2]
- [출처 3]
Quality Standards
1. Clarity
- One clear recommendation
- No hedging or vague language
- Specific and actionable
2. Evidence-Based
- Every claim has a source
- Confidence levels stated
- Conflicting info addressed
3. Context-Aware
- Tailored to specific project
- Considers team capabilities
- Addresses constraints
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.
- 11d ago First seen · 239 lines · 33 tokens per session scan A 85f290c766d0
decision-synthesizer is an agent published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,430 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.