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 spikeHongg/china-stock-research-skills --skill china-stock-research-orchestratorgit clone --depth 1 https://github.com/spikeHongg/china-stock-research-skillsWrote 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/spikehongg/china-stock-research-skills/china-stock-research-orchestrator)<a href="https://agentmods.dev/skills/spikehongg/china-stock-research-skills/china-stock-research-orchestrator"><img src="https://agentmods.dev/badge/skills/spikehongg/china-stock-research-skills/china-stock-research-orchestrator/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/spikehongg/china-stock-research-skills/china-stock-research-orchestrator"><img src="https://agentmods.dev/badge/skills/spikehongg/china-stock-research-skills/china-stock-research-orchestrator.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 | $0.00072 | $0.00813 |
| Opus 5 | $0.00036 | $0.00407 |
| Sonnet 5 | $0.00014 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
china-stock-research-orchestrator 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
China Stock Research Orchestrator
Route an A-share company through the right research workflow before doing deep analysis.
Non-Negotiable Rules
- Preserve strict separation between
Facts,Interpretation, andOpen Questions. - Require every key fact and number to carry an accessible source link.
- Prefer official disclosures, regulators, and public official portals over media and commentary.
- Use this skill to orchestrate the workflow, not to replace the six core modules.
- Default every intermediate and final output to Simplified Chinese unless the user explicitly requests another language.
Read First
skills/shared/references/source-registry.mdskills/shared/references/citation-standard.mdskills/shared/references/company-disclosure-map.mdskills/shared/references/research-output-template.mdskills/shared/references/analysis-pattern-selector.mdskills/shared/references/language-output-standard.mdskills/china-stock-research-orchestrator/references/routing-matrix.mdskills/china-stock-research-orchestrator/references/sector-overlay-escalation-rules.mdskills/china-stock-research-orchestrator/references/final-output-contract.md
Required Inputs
- Company name and ticker if available
- Research objective or key question
- As-of date if the user cares about a specific cutoff
- Optional hints about industry, business model, or suspected issues
When to Use
- Start a fresh A-share stock deep-dive.
- Turn a vague request like "analyze this stock" into a structured workflow.
- Decide which of the six core modules are necessary before going deep.
- Merge module outputs into one consistent research framework.
Workflow
- Identify the company's primary and secondary analysis patterns with
skills/shared/references/analysis-pattern-selector.md. - Use
skills/china-stock-research-orchestrator/references/routing-matrix.mdto decide which core modules are mandatory, optional, or skippable. - Decide whether a sector overlay is needed using
skills/china-stock-research-orchestrator/references/sector-overlay-escalation-rules.md. - Run the selected modules in the right order, usually
strategy -> business -> financial -> industry -> risk -> valuation. - Require each module to return mergeable
事实,解读, and待验证问题blocks in Simplified Chinese. - Merge the outputs using
skills/china-stock-research-orchestrator/references/final-output-contract.md.
What ships with it
3 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.
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 · 76 lines · 72 tokens per session scan A eccbd7d690fe
china-stock-research-orchestrator is a skill published in the GitHub repository spikeHongg/china-stock-research-skills (17 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 813 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 skills, from other repositories
private-company-research
A research workflow for private companies, meaning businesses whose shares are not traded on a public stock exchange. It uses several research roles to investigate the company in depth.
bottleneck-hunter
A research workflow for finding supply-chain bottlenecks—parts of global production where shortages or limited capacity may create investment opportunities.
earnings-team
A team-based workflow for reading financial reports through four parallel perspectives and preparing the result for publication on a public account.
investment-research
A broad stock-research workflow combining ideas associated with Warren Buffett, Charlie Munger, Duan Yongping, and Li Lu. It examines the business, its quality, its risks, and its value.
income-investment
AI Berkshire skill: Income Investment: Durable and Opportunistic Distribution Analysis. Source: skills/income-investment.md.
industry-funnel
An investing screen that narrows the full market down to three companies by evaluating industries through a value-investing process.