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 skills add atorber/qmt-trading-skill --skill qmt-bridge-execution-reviewgit clone --depth 1 https://github.com/atorber/qmt-trading-skillWrote 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/atorber/qmt-trading-skill/qmt-bridge-execution-review)<a href="https://agentmods.dev/skills/atorber/qmt-trading-skill/qmt-bridge-execution-review"><img src="https://agentmods.dev/badge/skills/atorber/qmt-trading-skill/qmt-bridge-execution-review/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/atorber/qmt-trading-skill/qmt-bridge-execution-review"><img src="https://agentmods.dev/badge/skills/atorber/qmt-trading-skill/qmt-bridge-execution-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 36 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00103 | $0.01554 |
| Opus 5.5 | $0.00041 | $0.00622 |
| Sonnet 5.5 | $0.00021 | $0.00311 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
qmt-bridge-execution-review 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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QMT Trading Skill · 交易复盘
实现状态：✅ 客观脚本 + 证据包；✅ 三角色专家规程（Agent）
目标
闭合「计划—执行—复盘」：
- 客观层（脚本）：委托/成交/滑点、盈亏拆解、不操作基线、规则标签、算法参考分
- 主观层（Agent）：投顾 / 基金经理 / 交易员并行评审 → 综合裁决（见 expert-review-protocol.md）
脚本
| 脚本 | 作用 |
|---|---|
scripts/daily_trade_report.py |
单账户；默认 --eval-mode=evidence → reports/daily_eval_evidence.json；--feishu-md |
scripts/combined_trade_report.py |
全账户综合；证据包 reports/combined_daily_eval_evidence.json |
产物路径（禁止写死机器绝对路径）
相对路径一律相对 工作区根（workspace_root()）：
| 布局 | 工作区根 | reports/ 位置 |
|---|---|---|
| 本仓库开发 | 仓库根（含 skills/） |
<repo>/reports/ |
| Agent 安装 | Skills 安装根（_shared 的父目录） |
<skills-root>/reports/ |
- 脚本 stderr 会打印实际写入的绝对路径；后续读写请用该路径或相对
reports/...，禁止把某台机器的C:\GitHub\...写进规程/提示词 - 可选覆盖：
QMT_TRADING_SKILL_ROOT（工作区根）或QMT_TRADING_SKILL_REPORTS（reports 目录）
# 推荐：客观报告 + 证据包
python skills/qmt-bridge-execution-review/scripts/daily_trade_report.py \
--host 127.0.0.1 --port 8080 --api-key KEY --feishu-md
# 双账户
python skills/qmt-bridge-execution-review/scripts/combined_trade_report.py \
--host 127.0.0.1 --port 8080 --api-key KEY --feishu-md
# 旧版模板评语（对比校准）
python skills/qmt-bridge-execution-review/scripts/daily_trade_report.py --eval-mode=rules --feishu-md
| 参数 | 说明 |
|---|---|
--eval-mode evidence|rules |
默认 evidence（事实+标签）；rules 旧模板叙事 |
--evidence-json [PATH] |
证据包路径（evidence 模式默认写出） |
--feishu-md [PATH] |
客观 Markdown（含第七节专家占位） |
--json |
stdout JSON（含 operation_evaluation） |
--no-eval |
跳过评价与证据 |
--market-turnover-yi / --no-philosophy-fetch |
同前 |
提示词示例
| 场景 | 提示词 |
|---|---|
| 三角色专家复盘（推荐） | 用投顾/基金经理/交易员三角色做今日复盘并综合裁决 |
| 客观报告 | 生成今日交易复盘（先出证据包） |
| 基线对比 | 列一下不操作少赚/多亏的明细 |
| 全账户 | 普通户+信用户综合复盘并做三角色评审 |
| 旧规则对照 | 用 rules 模式跑一版复盘对比算法分 |
操作规程（Agent）
health确认 Bridge；需要时按 qmt-bridge-setup 检测服务- 跑
daily_trade_report.py或combined_trade_report.py（--feishu-md） - 读取
reports/*_evidence.json— 禁止编造数字 - 按 expert-review-protocol.md 套用：
- 写入
reports/feishu_*_expert.md，合并替换客观 MD 第七节 - 同步飞书见 feishu-doc — 允许基于 evidence 写专家评语；禁止手写/篡改一～六客观章节
- 只输出报告，不下单
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/expert-review-protocol.md 2.8 KB
- references/personas/advisor.md 1.2 KB
- references/personas/fund-manager.md 1.2 KB
- references/personas/trader.md 1.2 KB
- references/thresholds.yaml 1.1 KB
- references/trading-philosophy.md 5.0 KB
- scripts/combined_trade_report.py 17 KB runs code
- scripts/daily_trade_report.py 13 KB runs code
- scripts/README.md 1.2 KB
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.
- 1mo ago Changed · -16 lines · -42 tokens per session 46f7ee0f665b
- 2mo ago First seen · 135 lines · 145 tokens per session scan A 52d1e5898846
qmt-bridge-execution-review is a skill published in the GitHub repository atorber/qmt-trading-skill (26 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,554 once invoked, about $0.0004 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 2026-08-30.
qmt-bridge-execution-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qmt-bridge-execution-reviewatorber/qmt-trading-skill | Skill | 26 | 1mo ago | MIT | A | 103 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |