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/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/generate-investor-portal)<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/generate-investor-portal"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/generate-investor-portal/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/fledgeling-co/fledgeling-plugins/generate-investor-portal"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/generate-investor-portal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
generate-investor-portal 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 yesterday.
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": "generate-investor-portal",
"description": "Generate a complete investor-portal record — theme tokens, section content, provenance-marked figures, imagery and motion — into a database from a company's DESIGN.md and a crawled company overview, so a new company is a generated record rather than new code and one generic renderer serves it at that company's own subdomain. Its distinguishing feature is that it ships the gate instead of describing it: assets/record-gate.mjs runs 600+ record-level checks with no server, no database and no network, and refuses the write rather than the read, so a rule added to it can never take a live portal down. The check that matters most is that a figure is not allowed to live in prose — a currency amount, a percentage or a date in any prose slot without a provenance object around it is refused, because that is the channel a plausible fabricated number actually arrives through, and a missing figure has to become a visibly marked unavailable state with a reason code instead. It treats the crawled overview as untrusted third-party content and carries a verbatim injection fence into every subagent brief and every paid image prompt; it refuses a republish before anything is crawled or generated rather than after; it measures accent contrast arithmetically on hex against role-aware floors so a brand colour is never rejected where it belongs; and it detects the defect no per-tenant gate can see, two companies publishing the same portal, by comparing three collision keys against the published peer set. Use it when someone wants an investor portal built, generated or refreshed for a company, wants a company onboarded onto a portal platform, or hands over a DESIGN.md plus a company overview and asks for a portal from them.",
"version": "1.3.2",
"author": {
"name": "Fledgeling",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 285 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed eb100dc1ab68
- 5d ago Changed 2cf37e5db43f
- 9d ago First seen · 10 lines scan A 3515f332bb3a
generate-investor-portal is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), 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 2026-08-31.
Other plugins, from other repositories
financial-ui-suite
Production-grade financial UI design skills for Claude Code. Two composable layers: financial-ui-patterns (correctness — tabular nums, semantic tokens, tick flash, accessibility, charts) and financial-ui-styles (aesthetic — 13 distinct visual systems: Bloomberg terminal, TradingView, Robinhood, Coinbase, Financial…
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
raven-mcp
Design-intelligence MCP server: audits pages, screens, and diffs for contrast, layout, tap targets, and consistency; carries a design system and a taste profile an agent can consult before writing UI code.
aio-visual-diff
Verify AI-built UI against design via measurement-driven diff — extracts computed CSS and bounding boxes through Chrome DevTools MCP, diffs against Figma reference or a frozen baseline, and feeds numerical deltas back to the agent. No screenshot eyeballing.
datarails-financeos
Datarails Finance OS integration - analyze financial data, detect anomalies, and generate insights.
financial-evidence
Read-only evidence for money markets, capital markets, China economy, bank risk, and market liquidity across LiquiLens, Undertow, Seiche, and Palimpsest.