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.
/plugin marketplace add fledgeling-co/fledgeling-pluginsnpx agentmods add plugins/fledgeling-co/fledgeling-plugins/dossier-reportgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsGrade A, and why
dossier-report 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.
What it actually says
{
"name": "dossier-report",
"description": "dossier-report: turn a research question into one published, uniquely-themed HTML page — a Dossier paid+free deep-research panel read in full, compiled into a claim graph, then designed from scratch around its own subject and published to <slug>.fledgeling.app. Ships three readings of the same argument over one claim graph (Primer / Brief / Technical), toggled by the reader, each independently and fully cited from one shared registry and working with JavaScript off, opening with a required TLDR band. Product and buying research also ships a verdict layer: three ranked picks per buyer category plus one overall winner with its cost and its weaknesses, where a paywalled Which?/RTINGS/Choice verdict counts as high-value evidence and every ranking renders as a marked inference. Every page gets its own visual language, light and dark both measured, GSAP as a hard requirement covering micro-interactions and choreography, conditional three.js behind a six-test gate, figures through dataviz in native CSS/DOM, hand-authored SVG or TanStack Charts compiled to static SVG at build time, imagery taken from the research sources with full provenance plus captioned media-gen-pro stills and clips, claim-local citations with source popups, a verified source registry, a measured divider-gutter rule, and the Dossier/Margin marketing chrome. Layout direction comes from a Mobbin trawl with a took/left ledger and /trawl divergence, routed through design-craft and ux-craft.",
"version": "2.4.0",
"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 — 485 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.
- 2d ago First seen · 10 lines scan A 976ad5883870
dossier-report is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 3d 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 2026-08-31.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.
ui-ux-pro-max
UI/UX design intelligence. Searchable local database with 84 styles, 192 palettes, 74 font pairings, 25 charts, and 22 stacks (React, Next.js, Vue, Nuxt.js, Nuxt UI, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP…