Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsnpx agentmods add skills/fledgeling-co/fledgeling-plugins/generate-investor-portalWrote 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/skills/fledgeling-co/fledgeling-plugins/generate-investor-portal)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/generate-investor-portal"><img src="https://agentmods.dev/badge/skills/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/skills/fledgeling-co/fledgeling-plugins/generate-investor-portal"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/generate-investor-portal.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00285 | $0.09822 |
| Opus 5 | $0.00143 | $0.04911 |
| Sonnet 5 | $0.00057 | $0.01964 |
| Haiku 4.5 | $0.00028 | $0.00982 |
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 4d 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 — 639 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate an investor portal
You are producing data, not a website. The website already exists: one generic Next.js
project (diolog-investor-portal) renders any company from a validated record. Your output is
that record.
Getting this wrong in the first five minutes is the expensive failure. If you find yourself writing HTML or CSS, stop — you have misread the task.
Using Gemini? Read gemini.md for this skill's task-specific calibration and artifact checks. Its older runs do not establish Gemini 3.8 capability limits: preserve the user's selected implementation lane, and apply a model-specific route only when the current model or an observed failure supports it.
First, three exits — before anything is crawled or generated
A run spends money in its first minute: two crawl skills, then image generation. Each of these is settled before that, not after.
-
Empty argument. Ask in one line which company and which category (
free/paid/report), then stop. -
A bare ticker or a bare company name. Resolve it to a company id in the Diolog database and say which one you resolved to. Two companies share a trading name more often than you expect; the wrong id writes a correct portal to the wrong address.
-
An existing record whose status is literally
published. That is the--republishdecision, and it is asked here, before the crawl. The refusal used to live at the write, so a run could crawl a site twice, generate paid imagery and then be told it could not proceed.Absent or draft → proceed.
published→ stop and ask. Anything else → treat as overwritable, so a future review state is safe by default and an unrecognised one cannot become publishable.
Where a canonical release index exists, check the content hash too, not only the status: the
duplicate-generation control the research prescribes is to check the release index and content hash
before crawl or paid generation, and return the canonical record if present
(references/evidence.md, E9). A byte-identical regeneration is spend with no change.
What ships with it
19 files beside SKILL.md 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/fixtures/derive.mjs 5.0 KB runs code
- assets/fixtures/fail-collides-with-peer.json 8.5 KB
- assets/fixtures/fail-fabricated-figure.json 8.4 KB
- assets/fixtures/fail-levy-evasion.json 5.6 KB
- assets/fixtures/fail-published-no-republish.json 8.3 KB
- assets/fixtures/pass-minimal.json 8.7 KB
- assets/fixtures/peers/eastcoast-freight-free.json 8.8 KB
- assets/mutate.mjs 7.7 KB runs code
- assets/record-gate.mjs 69 KB runs code
- assets/reference-theme.json 3.5 KB
- gemini.md 23 KB
- references/binding-decisions.md 4.9 KB
- references/evidence.md 21 KB
- references/imagery.md 7.9 KB
- references/record-shape.md 15 KB
- references/refused-ideas.md 6.4 KB
- references/tokens-and-motion.md 25 KB
- references/validate-and-prove.md 24 KB
- references/what-shipped-wrong.md 20 KB
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.
- 4d ago Changed · +6 tokens per session 2c8a23234f78
- 7d ago Changed · +70 lines 233a4cd370b3
- 11d ago First seen · 569 lines · 279 tokens per session scan A 6e9f3d617b39
generate-investor-portal is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 285 tokens to every session and 9,822 once invoked, about $0.0014 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 skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…