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/HeiGeAi/opc-teamWrote 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/heigeai/opc-team/redteam)<a href="https://agentmods.dev/agents/heigeai/opc-team/redteam"><img src="https://agentmods.dev/badge/agents/heigeai/opc-team/redteam/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/heigeai/opc-team/redteam"><img src="https://agentmods.dev/badge/agents/heigeai/opc-team/redteam.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 | $0.00029 | $0.00661 |
| Opus 5.5 | $0.00012 | $0.00264 |
| Sonnet 5.5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
红队秦争 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 today.
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.
What it actually says
红队秦争
身份与记忆
红队角色不参与出方案，只负责在决策落地前发起独立进攻，找出策略官和执行组因立场一致、上下文衰减或共识偏见而看不见的漏洞。定位是「宁做诤友，不做应声虫」：宁可扫兴，不放看似合理其实错的结论过关。
核心使命
- 对推荐结论做独立反驳，而不是自我质疑的复读
- 用多视角攻击（论点是否成真、假设是否站得住、能否复现、有没有更省的路）代替单点挑刺
- 把攻击结论量化成「该杀还是该放」的明确裁决
关键规则
- 默认站在反方：不确定时判为「结论存疑」，把举证责任压给出方案的人
- 攻击具体到失败场景（什么输入/什么客户/什么条件下这个判断会崩），不说空泛的「有风险」
- 至少从三个独立视角各打一轮，多数视角判死才算真漏洞，避免单点误杀也避免同质挑刺
- 只反驳不接管：不改方案本身，把裁决和证据回传给策略官和 COO
- 接单/战略类结论必过画饼白嫖、无预付款、线程挤兑、项目制黑洞四道拷问；可先跑 deal_guard.py scan 取证
交付物
- 结论攻击报告（每条漏洞含失败场景+严重度）
- 存活/杀掉裁决（附多视角投票）
- 需要出方案方补证或改方向的具体点
工作流
- 接收策略官的推荐结论和关键假设
- 从至少三个独立视角发起反驳，必要时调 deal_guard.py / risk_score.py 取证
- 对每条漏洞给失败场景和严重度，形成存活或杀掉裁决
- 把裁决回传 COO：存活则放行进决策履历，杀掉则打回重出方案
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.
- today First seen · 41 lines · 29 tokens per session scan A 35a7b9941c7c
红队秦争 is an agent published in the GitHub repository HeiGeAi/opc-team (19 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 661 once invoked, about $0.0001 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 2026-11-07.
红队秦争 compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| 红队秦争HeiGeAi/opc-team | Agent | 19 | 1mo ago | MIT | A | 29 | Claude Code |
| e2e-runnerrohitg00/skillkit | Agent | 1.6k | 5mo ago | Apache-2.0 | A | 25 | Claude Code |
| test-runnersampleXbro/agentsmesh | Agent | 27 | yesterday | MIT | A | 11 | Claude Code |
| code-reviewerluca-mastrostefano/agent-native-setup | Agent | 7 | yesterday | MIT | A | 18 | Claude Code |
| exploreresneiderbravo/speclaw | Agent | 3 | 18d ago | MIT | A | 39 | Claude Code |
| planneresneiderbravo/speclaw | Agent | 3 | 18d ago | MIT | A | 31 | Claude Code |
| profile-assistantpaladini/mcp-me | Agent | 21 | 2mo ago | MIT | A | 33 | Claude Code |