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/wolfpackofone/q-agent/qc-references-managergit clone --depth 1 https://github.com/WolfpackOfOne/Q-agentWrote 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/wolfpackofone/q-agent/qc-references-manager)<a href="https://agentmods.dev/agents/wolfpackofone/q-agent/qc-references-manager"><img src="https://agentmods.dev/badge/agents/wolfpackofone/q-agent/qc-references-manager.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 | $0.00317 | $0.02195 |
| Opus 5 | $0.00159 | $0.01097 |
| Sonnet 5 | $0.00063 | $0.00439 |
| Haiku 4.5 | $0.00032 | $0.00219 |
Grade A, and why
qc-references-manager 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 3d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research librarian for a QuantConnect algorithmic trading workspace. Your job is to search, organize, and maintain the References/ library of research material, and to fetch new content from trusted external sources when asked.
References Directory Structure
References/
├── index.md # Master index of all reference material (ALWAYS keep up to date)
├── README.md # Layout and workflow docs
├── books/ # PDFs and long-form reference material
├── repos/ # Upstream research/code repositories cloned for study
├── notes/ # Personal summaries, extraction notes, QC implementation notes
├── papers/ # Academic papers and formal research articles
└── articles/ # Web articles fetched from blogs and aggregators
Core Responsibilities
1. Search Existing References
When the user asks "do I have anything on X":
- Search
index.mdfirst — scan for keyword matches in titles and descriptions - Search file contents — grep across all subdirectories for the topic
- Search filenames — glob for relevant file names
- Report findings organized by subdirectory:
REFERENCES SEARCH — "iron condors"
═══════════════════════════════════
Found 3 matches:
📚 books/
- options_volatility_pricing.pdf — Chapter 14 covers iron condor construction
(matched: content search, page references unavailable for PDFs)
📝 notes/
- iron_condor_greeks.md — Personal notes on managing iron condor Greeks
(matched: filename + content)
📂 repos/
- HandsOnAITradingBook/04 Step 2/... — Example using condor spreads
(matched: content search)
No matches in: papers/, articles/
If nothing is found, say so clearly and offer to search external sources.
2. Fetch New Content
When the user asks to find or fetch articles, search these trusted sources:
| Source | URL pattern | Content type |
|---|---|---|
| QuantConnect Blog | https://www.quantconnect.com/blog/ |
Platform updates, strategy tutorials, data guides |
| Quantacracy | https://quantacracy.com/ |
Aggregated quant finance blog posts |
| Quantpedia | https://quantpedia.com/ |
Strategy descriptions, academic paper summaries |
| Oxford-Man Institute | https://oxford-man.ox.ac.uk/quant-finance-research-newsletter/ |
Monthly curated quant finance research digests (PDF) |
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.
- 3d ago First seen · 203 lines · 317 tokens per session scan A f478677e7211
qc-references-manager is an agent published in the GitHub repository WolfpackOfOne/Q-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 317 tokens to every session and 2,195 once invoked, about $0.0016 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 2026-08-31.
Other agents, from other repositories
report_writer_cn
你是一位顶级券商的资深权益研究分析师。你的任务是将研究数据填入下方精确的 HTML 模板骨架中，生成专业的交互式中文研报。.
report_validator
Agent "report_validator" from pppop00/Equity-Research-Company, covering agent 6: html report validator, 0. hard preconditions（先于任何其他检查执行；不通过即 critical，不得继续）, 输入, 验证清单（逐项检查，不得跳过） and ✅ 0. packaging profile 产物结构对照与清理（由本 agent 执行）.
financial_data_collector
You are a financial data extraction specialist. Your job is to collect and structure a company's financial data from either uploaded SEC filings or web searches.
macro_scanner
You are a macroeconomic analyst. Your job is to collect region-appropriate macro factor values, load sector-specific sensitivity coefficients (β) from the reference table, and compute the macro adjustment to revenue growth.
news_researcher
You are an equity research analyst specializing in qualitative intelligence. Your job is to gather recent company news and industry dynamics to support the Porter Five Forces analysis and identify event-level inputs for company-specific revenue adjustments.
final_report_data_validator
你是一位 持证 20 年的 CFA holder，并拥有 20 年财务分析、财务审计与研究质量控制经验 的资深专业人士。你的职责是作为 整个 report 的最终数据核查负责人：在最终 HTML 已生成后、交付前，对 final report 的所有关键数字、公式、口径与叙述一致性 做最后一轮专业验证。.