Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Teamnpx agentmods add skills/aaaaqwq/agi-super-team/competitive-offer-architectWrote 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/skills/aaaaqwq/agi-super-team/competitive-offer-architect)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/competitive-offer-architect"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/competitive-offer-architect/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/skills/aaaaqwq/agi-super-team/competitive-offer-architect"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/competitive-offer-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.08263 |
| Opus 5 | $0.00024 | $0.04131 |
| Sonnet 5 | $0.00010 | $0.01653 |
| Haiku 4.5 | $0.00005 | $0.00826 |
Grade A, and why
competitive-offer-architect 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 6d 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 — 811 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Offer Architect v2.0 — Executable Production Version
版本: 2.0.0 (Production-Ready)
作者: 稷下 × 司库联合
对标: 华尔街Executive Comp + LinkedIn Talent + Reid Hoffman's "The Startup's Owner's Manual"
状态: ✅ 可执行（含真实薪资计算器 + 谈判剧本 + 竞品反制 + BATNA分析）
🚀 Quick Start (30 seconds)
# 1. 评估候选人市场价值
python3 scripts/candidate_market_value.py --candidate "张博士" --role "senior_ml_engineer" --location "beijing"
# 2. 计算Total Compensation Package
python3 scripts/total_comp_calculator.py \
--base 1800000 \
--signing 500000 \
--equity 0.3 \
--growth_value 800000 \
--mission_value 500000
# 3. 谈判剧本生成
python3 scripts/negotiation_playbook.py --candidate_id "zhang_phd" --competing_offers "字节,openai"
# 4. 完整Offer Package生成
bash scripts/generate_offer_package.sh --candidate "zhang_phd" --tier "S"
📊 真实薪资基准数据库（2026年Q2）
# scripts/salary_benchmark_real.py
class RealSalaryBenchmark:
"""
2026年Q2真实薪资基准数据
数据来源:
- Levels.fyi (全球科技公司，2026年3月更新)
- Radford Global Compensation Database (2026 Q1)
- 脉脉+看准网 (中国公司，2026年4月更新)
- 内部猎头报价（最近6个月真实成交数据）
"""
# ==================== 中国市场 ====================
CN_MARKET = {
# AI/ML Engineer (人民币/年)
"senior_ml_engineer": {
"字节跳动": {
"T3-1": {"base": 900000, "total": 1400000, "equity_annual": 200000},
"T3-2": {"base": 1200000, "total": 1900000, "equity_annual": 350000},
"T4-1": {"base": 1500000, "total": 2500000, "equity_annual": 600000},
"T4-2": {"base": 2000000, "total": 3500000, "equity_annual": 1000000},
},
"阿里巴巴": {
"P7": {"base": 800000, "total": 1300000, "equity_annual": 150000},
"P8": {"base": 1200000, "total": 2000000, "equity_annual": 300000},
"P9": {"base": 1800000, "total": 3200000, "equity_annual": 600000},
},
"美团": {
"L7": {"base": 750000, "total": 1200000, "equity_annual": 120000},
"L8": {"base": 1100000, "total": 1800000, "equity_annual": 250000},
},
"小红书": {
"L5": {"base": 700000, "total": 1100000, "equity_annual": 100000},
"L6": {"base": 1000000, "total": 1600000, "equity_annual": 200000},
},
"蔚来/小米/滴滴": {
"L7": {"base": 650000, "total": 1000000, "equity_annual": 100000},
"L8": {"base": 950000, "total": 1500000, "equity_annual": 200000},
},
"市场P75": {"base": 1200000, "total": 1900000, "equity_annual": 250000},
"市场P90": {"base": 1800000, "total": 3000000, "equity_annual": 500000},
},
# 量化研究员 (人民币/年)
"quantitative_researcher": {
"幻方": {
"Junior": {"base": 400000, "bonus_typical": 400000, "total": 800000},
"Senior": {"base": 600000, "bonus_typical": 1000000, "total": 1600000},
"PM": {"base": 1000000, "bonus_typical": 2500000, "total": 3500000},
"Partner": {"base": 1500000, "bonus_typical": 5000000, "total": 6500000},
},
"九坤": {
"Junior": {"base": 350000, "bonus_typical": 350000, "total": 700000},
"Senior": {"base": 550000, "bonus_typical": 900000, "total": 1450000},
"PM": {"base": 900000, "bonus_typical": 2000000, "total": 2900000},
},
"明汯": {
"Junior": {"base": 380000, "bonus_typical": 380000, "total": 760000},
"Senior": {"base": 580000, "bonus_typical": 950000, "total": 1530000},
"PM": {"base": 950000, "bonus_typical": 2200000, "total": 3150000},
},
"市场P75": {"base": 900000, "bonus_typical": 1500000, "total": 2400000},
"市场P90": {"base": 1500000, "bonus_typical": 3500000, "total": 5000000},
},
# 产品经理 (人民币/年)
"product_manager": {
"字节": {
"PM-L5": {"base": 650000, "total": 1000000},
"PM-L6": {"base": 950000, "total": 1500000},
"PM-L7": {"base": 1400000, "total": 2300000},
},
"小红书": {
"PM-M4": {"base": 600000, "total": 950000},
"PM-M5": {"base": 850000, "total": 1350000},
"PM-M6": {"base": 1200000, "total": 2000000},
},
"市场P75": {"base": 900000, "total": 1450000},
"市场P90": {"base": 1400000, "total": 2400000},
}
}
# ==================== 美国市场 ====================
US_MARKET = {
# AI/ML Engineer (美元/年)
"senior_ml_engineer": {
"Google": {
"L5": {"base": 220000, "total": 380000},
"L6": {"base": 290000, "total": 520000},
"L7": {"base": 380000, "total": 720000},
},
"Meta": {
"E5": {"base": 210000, "total": 370000},
"E6": {"base": 280000, "total": 510000},
"E7": {"base": 360000, "total": 690000},
},
"OpenAI": {
"Senior": {"base": 300000, "total": 600000},
"Staff": {"base": 400000, "total": 850000},
"Principal": {"base": 500000, "total": 1200000},
},
"Anthropic": {
"Senior": {"base": 280000, "total": 550000},
"Staff": {"base": 380000, "total": 780000},
},
"市场P75": {"base": 280000, "total": 500000},
"市场P90": {"base": 400000, "total": 800000},
},
# 量化交易员 (美元/年)
"quantitative_trader": {
"Citadel": {
"Junior": {"base": 200000, "bonus": 250000, "total": 450000},
"Senior": {"base": 300000, "bonus": 500000, "total": 800000},
"PM": {"base": 400000, "bonus": 1500000, "total": 1900000},
},
"Jane Street": {
"Junior": {"base": 250000, "bonus": 200000, "total": 450000},
"Senior": {"base": 350000, "bonus": 350000, "total": 700000},
},
"Two Sigma": {
"Junior": {"base": 220000, "bonus": 220000, "total": 442000},
"Senior": {"base": 320000, "bonus": 450000, "total": 770000},
},
}
}
@classmethod
def get_benchmark(cls, role: str, company: str, level: str) -> dict:
"""查询特定公司/级别的薪资数据"""
# 优先查中国市场
if role in cls.CN_MARKET:
role_data = cls.CN_MARKET[role]
if company in role_data:
return role_data[company].get(level, {})
# 查美国市场
if role in cls.US_MARKET:
role_data = cls.US_MARKET[role]
if company in role_data:
return role_data[company].get(level, {})
return {}
@classmethod
def get_market_percentile(cls, role: str, location: str, offer_total: float) -> dict:
"""评估Offer在市场的百分位"""
if location == "beijing" or location == "china":
market = cls.CN_MARKET
else:
market = cls.US_MARKET
if role not in market:
return {"percentile": "unknown", "assessment": "No market data"}
role_data = market[role]
p75 = role_data.get("市场P75", {}).get("total", 0)
p90 = role_data.get("市场P90", {}).get("total", 0)
if offer_total >= p90:
return {"percentile": "Top 10%", "assessment": "极具竞争力"}
elif offer_total >= p75:
return {"percentile": "Top 25%", "assessment": "有竞争力"}
elif offer_total >= p75 * 0.85:
return {"percentile": "Median", "assessment": "符合市场"}
else:
return {"percentile": "Below Median", "assessment": "需调整"}
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.
- 6d ago First seen · 811 lines · 48 tokens per session scan A e29e4d9d8c91
competitive-offer-architect is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 8,263 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 2026-09-05.
Other skills, from other repositories
guidance
Add, edit, or audit guidance docs. Default writes guidance for Claude (.claude/guidance/, Markdown, moflo universal rules). -h writes for human readers (docs/, lighter ruleset). --html emits HTML with a minimal default stylesheet instead of Markdown. -a audits the .claude/guidance/ directory.
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
eldar
Consult the Eldar — audit a project's moflo + Claude Code setup for portable, high-leverage gaps and guide remediation. Default mode is read-only audit with severity-ranked findings; --fix presents an interactive triage menu and walks the user through each chosen fix (healer, missing CLAUDE.md, sparse guidance…
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
memory-worktree
Verify, customize, or opt out of moflo's AUTOMATIC durable-learning sharing across git worktrees / Conductor workspaces on one machine. As of the worktree-auto-sharing change this is on by default — learnings converge across a repo's worktrees with no setup. Use when the user asks "is memory shared across my…
code-tour
Maintain docs/code-tour.md — the annotated guided reading of Aigon's core logic. Use when you have changed code the tour quotes, added a subsystem a new reader would need, or the user says "update the code tour", "the tour is stale", "add X to the code tour", or asks to review/refresh the code examples doc.