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 KCNyu/clawock --skill portfolio-swarm-reviewgit clone --depth 1 https://github.com/KCNyu/clawockWrote 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/kcnyu/clawock/portfolio-swarm-review)<a href="https://agentmods.dev/skills/kcnyu/clawock/portfolio-swarm-review"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/portfolio-swarm-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/kcnyu/clawock/portfolio-swarm-review"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/portfolio-swarm-review.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 | $0.00090 | $0.03228 |
| Opus 5 | $0.00045 | $0.01614 |
| Sonnet 5 | $0.00018 | $0.00646 |
| Haiku 4.5 | $0.00009 | $0.00323 |
Grade A, and why
portfolio-swarm-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 12d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portfolio Swarm Review
Multi-agent portfolio review. Structure mirrors the TauricResearch/TradingAgents design — analysts (Tier 1) → researchers (Tier 2) → risk debators + judge (Tier 3). Each tier is distinct in the output; the Judge synthesizes. (The reference repo is no longer cloned locally; the structure is recorded here.)
Required reads
In this order:
/root/.openclaw/workspace/MEMORY.md/root/.openclaw/workspace/portfolio.json/root/.openclaw/workspace/INVESTMENT_SOP.md/root/.openclaw/workspace/TOOLS.mdfor data chain detail../daily-deep-brief/references/technical-playbooks.mdbefore any add / average-down synthesis
Active vs exited comes from portfolio.json alone (shares > 0 / == 0); the
hand-maintained summary that used to be step 3 drifted 3.5 months and was deleted
(#1067).
Fresh data rule
Refresh quotes before producing conclusions:
/root/.local/bin/clawock analyze-us # US 7-route fallback
/root/.local/bin/clawock analyze-hk # HK Tencent + Eastmoney full-batch cross-check/fallback → stooq → yfinance
If a leg is stale, name the exact ticker and limit confidence on conclusions involving it. 00100 only has Tencent — flag explicitly if that leg fails. KR linkage: 07709/07747 are exited, but SKHY (SK Hynix ADR) can be held — check
portfolio.json rather than assuming the whole chain is dead.
Holdings bucketing — read each run, do not hardcode
Pull live set from portfolio.json (shares > 0). Stable bucket structure; contents drift:
- US growth / single-name beta — active US non-leveraged growth names
- US leverage ETF — anything
is_leveraged_etf: true - US theme / special situation — catalyst-driven names
- HK lower-beta core — index/sector ETFs (e.g. 03032, 03033)
- HK single-name — individual equities (e.g. 00100 AI, 02208 wind)
- HK leverage ETF — 2x/3x recipes (e.g. 07226)
Regime detection (run first)
Before any role analysis, classify current regime — this calibrates everything downstream:
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.
- 12d ago First seen · 212 lines · 90 tokens per session scan A 0360641e01c1
portfolio-swarm-review is a skill published in the GitHub repository KCNyu/clawock (14 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 3,228 once invoked, about $0.0005 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 skills, from other repositories
tushare
A Python interface to Tushare, a financial-data service providing market, company, fund, futures, and other finance-related data. It shows how to authenticate and query the service into pandas tables.
credit-analysis
A framework for analysing bonds and other fixed-income investments, including issuer credit quality, interest-rate sensitivity, credit spreads, and default risk. A credit rating estimates how likely an issuer or specific bond is to repay its debt.
financial-expense-automation
An expense-receipt workflow that reads PDF and image attachments, extracts their details, checks whether they are valid expense receipts, and records them in Feishu Bitable, a cloud table service.
vibe-trading
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest →…
quant-statistics
Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.
crypto-monitor
A scheduled cryptocurrency price checker that uses CoinGecko, a service providing market data. It tracks Bitcoin, Ethereum, and Litecoin in US dollars and Chinese yuan, including their change over the past 24 hours.