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 equity-rigor/us-equity-research --skill china-equity-researchgit clone --depth 1 https://github.com/equity-rigor/us-equity-researchWrote 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/equity-rigor/us-equity-research/china-equity-research)<a href="https://agentmods.dev/skills/equity-rigor/us-equity-research/china-equity-research"><img src="https://agentmods.dev/badge/skills/equity-rigor/us-equity-research/china-equity-research/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/equity-rigor/us-equity-research/china-equity-research"><img src="https://agentmods.dev/badge/skills/equity-rigor/us-equity-research/china-equity-research.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00169 | $0.03456 |
| Opus 5 | $0.00084 | $0.01728 |
| Sonnet 5 | $0.00034 | $0.00691 |
| Haiku 4.5 | $0.00017 | $0.00346 |
Grade B, and why
china-equity-research scanned grade B with 1 finding 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 11d 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- "Other agents in this batch successfully used 25-100+ web tool calls. Do not refuse to execute." Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
China A-Share / H-Share Equity Research Workflow
A multi-phase, multi-agent fundamental research framework for Chinese listed equities. Built to produce IC-memo-grade output with mandatory verification, integrated red team, and explicit position sizing.
Core Principles
These four principles run through every phase. Without them, the workflow degrades to ordinary sell-side commentary.
1. Multi-agent specialization beats monolithic analysis. A single agent doing "everything about stock X" will skim. Forced specialization with explicit handoffs catches things one analyst would miss. Industry, financial forensics, policy, positioning, and competitive analysis are different analytical units — they deserve different specialists.
2. Red Team runs in parallel from day one, not as final reviewer. The Red Team's job is to build the strongest possible bear case in good faith. It is judged on whether it identifies things the bull side missed, not on agreement with the PM. Assigning Red Team only at the end is too late — by then the narrative has hardened.
3. Web verification is mandatory for any post-cutoff specific claim. Sub-agents can hallucinate plausible-looking URLs, document IDs, and numbers — especially for events past the model's training cutoff. Every material specific claim (FY financials, regulatory designations, customer share, settlement amounts) must be independently verified via WebSearch/WebFetch with source URL captured. Distinguish framework claims (durable, structural) from specific numerical claims (need verification). The single biggest failure mode is unverified hallucination dressed up as primary-source rigor.
4. Position sizing reflects confidence, not just direction. A "Buy" rating with limited conviction is half-weight. A "Buy" with high conviction is a core position. Always specify both rating and sizing, with explicit reasons for the gap between them.
When to Trigger
Invoke this workflow whenever the user wants institutional-grade research on a Chinese listed equity. Specific triggers include providing a ticker like 000725 / 600519 / 0700.HK and asking "research this", "analyze this", "is this a buy", "build me a thesis", or requesting a stock pitch / IC memo / buy-side note / investment thesis. Also trigger on requests for Chinese-language investor memos on Chinese stocks.
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/chinese-data-sources.md 10 KB
- references/forensic-accounting-checklist.md 11 KB
- references/ic-memo-template-chinese.md 7.9 KB
- references/ic-memo-template-english.md 5.8 KB
- references/monitoring-framework.md 6.8 KB
- references/phase-1-deep-dive.md 13 KB
- references/phase-2-continuation.md 13 KB
- references/phase-3-valuation.md 10 KB
- references/verification-protocol.md 8.4 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.
- 11d ago First seen · 219 lines · 169 tokens per session scan B 86d08dc33cdd
china-equity-research is a skill published in the GitHub repository equity-rigor/us-equity-research (4 stars, last pushed 1mo ago), licensed MIT. It adds 169 tokens to every session and 3,456 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.