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.
git clone --depth 1 https://github.com/terrylica/cc-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/plugins/terrylica/cc-skills/quant-research)<a href="https://agentmods.dev/plugins/terrylica/cc-skills/quant-research"><img src="https://agentmods.dev/badge/plugins/terrylica/cc-skills/quant-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/plugins/terrylica/cc-skills/quant-research"><img src="https://agentmods.dev/badge/plugins/terrylica/cc-skills/quant-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
quant-research 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 today.
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.
What it actually says
{
"name": "quant-research",
"description": "Quantitative research metrics: SOTA evaluation for range bars, Sharpe ratios with daily aggregation, ML prediction quality (IC, autocorrelation), crypto-specific considerations",
"version": "34.10.0",
"source": "./plugins/quant-research",
"category": "trading",
"author": {
"name": "terrylica",
"url": "https://github.com/terrylica"
},
"keywords": [
"quant",
"range-bars",
"sharpe-ratio",
"metrics",
"evaluation",
"crypto",
"ml",
"prediction-quality",
"ic",
"psr",
"wfo"
],
"strict": false
}What it installs
The manifest is a name and a version. 8 skills travel with it, and installing the plugin installs all of them — 409 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill adaptive-wfo-epoch A 36 tokens
- Skill evolutionary-metric-ranking A 25 tokens
- Skill backtesting-py-oracle A 30 tokens
- Skill opendeviation-eval-metrics A 42 tokens
- Skill zigzag-pattern-classifier A 38 tokens
- Skill exchange-session-detector A 32 tokens
- Skill sharpe-ratio-non-iid-corrections A 172 tokens
- Skill odb-microstructure-forensics B 34 tokens
What ships with it
2 files beside marketplace.json#quant-research 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.
- today Changed 4e843ef272fc
- yesterday Changed a7493a87ecd4
- 2d ago Changed 8a44cf0309c0
- 3d ago Changed 09063324d064
- 4d ago Changed dbbb5d692f0b
- 5d ago Changed 0cd0f8789285
- 7d ago Changed · -1 lines 6fa514c655e5
- 9d ago Changed e70f9926a4f6
- 10d ago Changed dd7ca68d8c8a
- 11d ago First seen · 26 lines scan A 2c2505254586
quant-research is a plugin published in the GitHub repository terrylica/cc-skills (1 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-05.
Other plugins, from other repositories
cost-guardian
Zero-setup cost tracking and budget management for Claude Code. Real-time burn rate, budget guardrails, ASCII reports, and pre-task cost estimation — all without external dependencies.
consulting-toolkit
Multi-agent consulting system with an /engagement orchestration command, an Engagement Manager quality gate, and Research, Finance, Deck, and Due Diligence agents. Includes 17 consulting slash commands, deliverable templates, strategy frameworks, and an 8-tool Financial Intelligence MCP server for real-time financial…
real-estate-investment
Comprehensive real estate investment analysis plugin with financial modeling, market data APIs, deal analysis agents, and tax-aware structuring. Covers all property types: residential, commercial, multifamily, short-term rentals, and land development.
tradingview
AI-powered access to TradingView market screening - filter stocks, forex, crypto, and ETFs by 75+ fundamental and technical metrics.
billing-system
Generate subscription billing with metered usage.
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.