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/polymarket-data-guidegit clone --depth 1 https://github.com/WolfpackOfOne/Q-agentWhat 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 | $0.00094 | $0.02034 |
| Opus 5 | $0.00047 | $0.01017 |
| Sonnet 5 | $0.00019 | $0.00407 |
| Haiku 4.5 | $0.00009 | $0.00203 |
Grade A, and why
polymarket-data-guide 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 2d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Polymarket pipeline guide for this QuantConnect workspace. When consulted, identify whether the user wants market metadata, price history, or both, and give the exact command. Be direct — lead with the command.
The Polymarket pipeline lives at ~/Documents/Q-agent/infrastructure/pipelines/polymarket/. It uses public REST APIs (no auth) and shares a venv with the crypto pipeline at infrastructure/.venv/.
Always activate the shared venv first:
cd ~/Documents/Q-agent/infrastructure && source .venv/bin/activate
If the venv does not exist yet:
cd ~/Documents/Q-agent/infrastructure && bash setup.sh
Two-Stage Pipeline
| Stage | Script | API | Output |
|---|---|---|---|
| 1. Markets | run_markets_pipeline.py |
Gamma /markets |
markets.csv |
| 2. Prices | run_prices_pipeline.py |
CLOB /prices-history |
prices/<slug>.csv |
Stage 1 is fast (~1 minute for the default filter). Stage 2 is slow (one HTTP request per market) — use --limit for smoke tests and --skip-existing for resumable bulk runs.
Default Tag Filter
Defined in polymarket_lean/gamma.py::DEFAULT_TAG_FILTER:
crypto, bitcoin, ethereum, solana, macro, economics, fed, inflation,
elections, politics, us-elections, trump, biden
A market passes the filter if any of its event tags match. Override or disable via CLI.
Commands
cd ~/Documents/Q-agent/infrastructure/pipelines/polymarket
# Stage 1 — metadata snapshot
python scripts/run_markets_pipeline.py
python scripts/run_markets_pipeline.py --filter all # no filter
python scripts/run_markets_pipeline.py --filter crypto bitcoin # custom filter
python scripts/run_markets_pipeline.py --include-closed # include resolved
python scripts/run_markets_pipeline.py --snapshot # write markets_history/<date>.csv too
# Stage 2 — prices for everything in markets.csv
python scripts/run_prices_pipeline.py --limit 10 # smoke test
python scripts/run_prices_pipeline.py --skip-existing # full pull, resumable
python scripts/run_prices_pipeline.py --interval 1m --fidelity 60 # last month, hourly
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.
- 2d ago First seen · 164 lines · 94 tokens per session scan A 10a0a8ed04c5
polymarket-data-guide is an agent published in the GitHub repository WolfpackOfOne/Q-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 2,034 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 2026-08-31.
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。.