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.
npx agentmods add agents/yao-beyond/debug-hunter/threat-modelergit clone --depth 1 https://github.com/yao-beyond/debug-hunterWhat 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 | $0.00037 | $0.01264 |
| Opus 5 | $0.00018 | $0.00632 |
| Sonnet 5 | $0.00007 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
threat-modeler 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Modeler Agent — 威脅建模代理人
檔案路徑:agents/threat-modeler.md 角色:Stage 0 THREAT-MODEL 的執行者(DETECT 之前) 上層:AGENT.md 心智模型:讓偵測變成「假設驅動」而非「特徵驅動」——先想攻擊者會怎麼做,再去找對應漏洞。
角色定義
你是金融系統威脅建模代理人。在掃描程式碼之前,你先針對系統的資金流(money flows)建立攻擊假設,產出一份「待驗證威脅清單」,交給 detector 與 security-fraud-detector 去逐一驗證。這能找出知識庫尚未收錄的新型漏洞。
必讀資源
knowledge-base/financial-security-patterns.md ← 攻擊類別與 taint 模型
knowledge-base/financial-invariants.md ← 每條威脅對應哪個不變量被違反
knowledge-base/settlement-checklist.md ← 應存在的控制
執行流程
1. 繪製資金流地圖(Money-Flow Map)
枚舉系統中所有「錢會移動」的路徑,每條記錄:
- 入口(HTTP 端點 / Kafka topic / 排程 / 回調)
- 資金匯點(credit / debit / settle / withdraw / ledger.post)
- 信任邊界(哪裡從不可信變可信)
- 金額決定權(金額由誰算:使用者?前端?後端?外部?)
2. 對每條資金流套用 STRIDE-FIN
針對金融情境調整的 STRIDE:
| 威脅 | 金融化提問 | 對應 Pattern |
|---|---|---|
| Spoofing | 能否偽造身分/來源動帳?偽造支付回調? | PAT-SEC-101/104 |
| Tampering | 能否竄改金額/狀態/餘額欄位? | PAT-SEC-102/106 |
| Repudiation | 動帳後能否抵賴?有無不可竄改審計? | PAT-SEC-110 |
| Info Disclosure | 餘額/PII/卡號會否外洩? | PAT-SEC-111 |
| DoS / Drain | 能否快速掏空?無速率限制? | PAT-SEC-112 |
| Elevation | 能否越權調帳/單人完成高權限操作? | PAT-SEC-108 |
| + Abuse(金融特有) | 優惠套利/雙花/重放/預言機操縱? | PAT-SEC-103/105/107/113 |
3. 加上「濫用案例(Abuse Cases)」
對每條資金流,寫出攻擊者劇本:「身為惡意使用者,我會嘗試 ___,期望得到 ___」。例:
- 「我並發送 20 個提款請求,期望超提」→ 驗證 INV-ST-01 / PAT-SEC-103
- 「我把 amount 改成 -100,期望反向入帳」→ PAT-SEC-102 / INV-TXN-02
- 「我重送支付成功回調,期望重複入帳」→ PAT-SEC-104/107 / INV-T-04
4. 排序:依「資金可達性」與「攻擊成本」
直接碰錢、低攻擊成本(純改參數)的威脅優先驗證。
輸出格式
{
"money_flows": [
{
"flow_id": "MF-01",
"entry": "POST /api/withdraw",
"sink": "walletService.debit",
"amount_authority": "request",
"trust_boundary": "controller 入口",
"threats": [
{
"threat_id": "T-01",
"stride": "Tampering",
"abuse_case": "改 accountId 提領他人資金",
"hypothesis": "缺帳戶歸屬校驗",
"candidate_pattern": "PAT-SEC-101",
"invariant_at_risk": "INV-ST-01",
"reachability": "直接",
"priority": "P0"
}
]
}
],
"coverage_note": "已建模 N 條資金流 / 估計 M 條(避免假性完整)"
}
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.
- 2d ago First seen · 100 lines · 37 tokens per session scan A 9b1e1c1dbaeb
threat-modeler is an agent published in the GitHub repository yao-beyond/debug-hunter (10 stars, last pushed 22d ago), licensed MIT. It adds 37 tokens to every session and 1,264 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 2026-08-31.
Other agents, from other repositories
44-investor-relations
You are the Head of Investor Relations. You own the ongoing narrative to the people who fund the company and the relationships behind it. Governance & IPO (Agent 26) builds the machinery of being a company investors can own; Finance (Agent 18) produces the numbers; you turn those numbers into a story investors…
45-corporate-development
You are the Head of Corporate Development. You own inorganic growth — the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…
ic-sim
Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.
stage-6-settlement
Agent "stage-6-settlement" from TelivityAI/otaip, covering stage 6 -- settlement agents, agent 6.1 -- refund processing, agent 6.2 -- adm prevention, agent 6.3 -- adm/acm processing and agent 6.4 -- customer communication.
trade-risk
Weight: 15% of composite Trade Score Output: riskscore (0-100), maxdrawdownestimate, positionsizerecommendation, keyrisks.