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/beepboop2025/financial-evidence-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/beepboop2025/financial-evidence-skills/gemini-extension)<a href="https://agentmods.dev/plugins/beepboop2025/financial-evidence-skills/gemini-extension"><img src="https://agentmods.dev/badge/plugins/beepboop2025/financial-evidence-skills/gemini-extension/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/beepboop2025/financial-evidence-skills/gemini-extension"><img src="https://agentmods.dev/badge/plugins/beepboop2025/financial-evidence-skills/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
financial-evidence 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 5d 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.
What it actually says
{
"name": "financial-evidence",
"version": "0.1.15",
"description": "Read-only GIFT City, forex, gold, money-market, capital-market, China-economy, bank-risk and liquidity evidence.",
"mcpServers": {
"financial-evidence": {
"httpUrl": "https://agents.seiche.info/products/financial-evidence/mcp",
"timeout": 30000,
"description": "Hosted read-only research workspace with bounded operational measurement.",
"includeTools": [
"financial_evidence_workflow",
"financial_evidence_datasets",
"financial_evidence_funding_review",
"financial_evidence_query",
"financial_evidence_sources",
"financial_evidence_route",
"financial_evidence_packet",
"financial_evidence_agent_query",
"financial_evidence_review"
]
}
}
}
What ships with it
54 files beside gemini-extension.json 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.
- assets/logo-400.png 25 KB
- assets/logo.svg 811 B
- assets/README.md 337 B
- examples/trading/feed-pilot.py 1.4 KB runs code
- scripts/__init__.py 68 B runs code
- scripts/audit_distribution_gaps.py 26 KB runs code
- scripts/backup_funding_review.py 6.5 KB runs code
- scripts/backup_institutional_packets.py 7.1 KB runs code
- scripts/build_api_kit.py 8.6 KB runs code
- scripts/build_bank_media_brief.py 20 KB runs code
- scripts/build_excel_office_addin.py 2.0 KB runs code
- scripts/build_funding_media_brief.py 26 KB runs code
- scripts/build_google_office_addon.py 2.0 KB runs code
- scripts/build_hosted_noisefloor_kit.py 8.2 KB runs code
- scripts/build_media_catalog.py 14 KB runs code
- scripts/build_newsroom_reuse_kit.py 21 KB runs code
- scripts/build_office_kit.py 2.2 KB runs code
- scripts/build_onboarding.py 2.8 KB runs code
- scripts/build_platform_hub.py 17 KB runs code
- scripts/build_product_plugins.py 15 KB runs code
- scripts/build_research_kit.py 1.9 KB runs code
- scripts/build_research_watch.py 716 B runs code
- scripts/build_runtime_operations.py 2.3 KB runs code
- scripts/build_task_workflows.py 5.9 KB runs code
- scripts/capture_funding_review.py 29 KB runs code
- scripts/check_funding_review.py 24 KB runs code
- scripts/create_office_fixtures.cjs 931 B runs code
- scripts/observe_agent_distribution.py 14 KB runs code
- scripts/observe_funding_reliability.py 2.2 KB runs code
- scripts/office_adoption.py 9.7 KB runs code
- scripts/office_native/accept.py 22 KB runs code
- scripts/office_native/images.json 763 B
- scripts/office_native/README.md 2.7 KB
- scripts/office_native/test_verify_cells.py 2.9 KB runs code
- scripts/office_native/verify_cells.py 3.9 KB runs code
- scripts/offsite_funding_review.py 9.7 KB runs code
- scripts/plan_hosted_migration.py 4.1 KB runs code
- scripts/power_query_native/accept.py 3.1 KB runs code
- scripts/power_query_native/generate.py 11 KB runs code
- scripts/power_query_native/README.md 1.9 KB
- scripts/reconcile_funding_packet.py 2.2 KB runs code
- scripts/restore_reliability_ledger.py 2.3 KB runs code
- scripts/templates/noisefloor_hosted_client.py 3.1 KB runs code
- scripts/verify_excel_taskpane.md 2.1 KB
- scripts/verify_excel_taskpane.py 16 KB runs code
- scripts/verify_hosted_registry.py 3.3 KB runs code
- scripts/verify_office_files.py 5.0 KB runs code
- scripts/verify_office_queries.cjs 838 B runs code
- scripts/verify_openbb_extension.py 1.8 KB runs code
- scripts/verify_openbb_workspace.py 4.0 KB runs code
- scripts/verify_published_mcp.py 5.8 KB runs code
- scripts/verify_pypi_metadata.py 5.2 KB runs code
- scripts/verify_remote_mcp.py 7.5 KB runs code
- scripts/verify_research_tools.py 1.3 KB runs code
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.
- 5d ago Changed 3efe2b136ae0
- 7d ago Changed 6aa6dab290ef
- 9d ago Changed cc2462c6c405
- 10d ago Changed a0484998694a
- 12d ago Changed · +6 lines afef86965b30
- 18d ago Changed 509948d902d4
- 21d ago Changed 400d75942a64
- 1mo ago First seen · 18 lines scan A 13faf70d20ca
financial-evidence is a plugin published in the GitHub repository beepboop2025/financial-evidence-skills (1 stars, last pushed 6d ago), 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 2026-09-07.
Other plugins, from other repositories
eodhd-api
Developer-first financial data for Claude — 150k+ tickers, 70+ exchanges, real-time & historical prices, fundamentals, options, technicals, news, sentiment, macro indicators, ESG, and more via EODHD API and MCP Server.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
tako
Tako's proprietary knowledge graph as MCP tools — live financial, macroeconomic, and company data as interactive, citation-backed charts — plus bundled lookup and research skills.
tako
Tako MCP grounds your agent in two kinds of knowledge at once: proprietary structured data from trusted providers, and full web search. The curated side covers company financials, macroeconomic indicators, website traffic, sports, US government spending, and more. One tool call returns typed values with named sources…
equibles
US stock research from SEC filings, financial statements, earnings call transcripts, insider trades and 13F holdings through the hosted Equibles MCP server.
equibles
Financial research with SEC filings, company financials, institutional holdings, earnings calls, prices, options, and macroeconomic data.