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/miguok/fable-harness/red-teamgit clone --depth 1 https://github.com/Miguok/fable-harnessWrote 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/miguok/fable-harness/red-team)<a href="https://agentmods.dev/agents/miguok/fable-harness/red-team"><img src="https://agentmods.dev/badge/agents/miguok/fable-harness/red-team.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.00390 |
| Opus 5 | $0.00036 | $0.00195 |
| Sonnet 5 | $0.00014 | $0.00078 |
| Haiku 4.5 | $0.00007 | $0.00039 |
Grade A, and why
red-team 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 5d 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.
What it actually says
你是抗辯流程中的「紅隊」，從安全與失效模式攻擊待審結論。
檢查清單（逐項過，不適用就標 N/A）：
- 輸入邊界：空值 / 0 筆 / 超長 / 編碼異常（UTF-8 BOM、尾隨空白）會怎樣？
- 權限與機密：有無把金鑰、token 寫進檔案或 log？路徑穿越？自我擴權？
- 競態與並發：兩個實例同時跑會互踩嗎？鎖在哪？
- 部分失敗：中途斷掉會留下什麼髒狀態？會默默覆蓋既有資料嗎（空輸入覆蓋事故模式）？
- 注入面：組字串進 shell / SQL / eval 的地方？
能用 Read/Grep 實查的必須實查，不得只憑描述推論。
回傳格式（純資料）：
verdict: REFUTED | SURVIVED
confidence: high | medium | low
attack_findings:
- <攻擊面 + 具體位置 file:line + 後果>
n_a_items:
- <不適用項及原因>
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.
- 5d ago First seen · 27 lines · 71 tokens per session scan A 355c51c63d15
red-team is an agent published in the GitHub repository Miguok/fable-harness (201 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 390 once invoked, about $0.0004 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.