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/deck-craft)<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/deck-craft"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/deck-craft/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/deck-craft"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/deck-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
deck-craft 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 1mo 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": "deck-craft",
"version": "1.17.1",
"description": "Build, review or convert a slide deck across three targets from one body of craft: a self-contained fixed-stage HTML presentation, lecturn.deck/1 JSON with a .pptx round-trip, or an investor deck assembled from a bundled library of 200 slide layouts in 27 families and 21 recipes. Carries its own design layer rather than depending on a general design skill — a supplied DESIGN.md or token file is binding, a direction is authored on three named axes when no brand exists, and type is sized from a viewing-angle derivation rather than from web habit. Deck-specific narrative discipline: the title sequence written before any slide because the titles read in order are the argument, speaking-versus-reading density as an explicit fork, one idea per slide, and a named slide count treated as a contract. Ships a deterministic preflight gate that runs in a headless browser and is built to be unable to pass silently: the probe carries its own blocker and warning policy plus a stated consequence for every finding, refuses a config key it does not recognise, and echoes its configuration back so the runner can prove the settings that were asked for actually arrived. Only exit 0 is a pass — a probe that returned nothing, a config that never landed, a check that threw and a run that examined zero slides each get their own code and their own refusal. Regulated decks add per-slide disclosure checks sourced to SEC Regulation G and Item 10(e), the December 2022 Compliance and Disclosure Interpretations on equal-or-greater prominence, and ASIC RG 230; chart integrity covers truncated baselines, dual axes and inverted axes; and given the source document it cross-checks every figure on the deck against it, because fabrication arrives as texture around a real number rather than as an invented headline.",
"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 — 229 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.
- 1mo ago Changed 540b85422af1
- 1mo ago Changed 84818d1f3621
- 1mo ago First seen · 10 lines scan A ad34157e9972
deck-craft is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d 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 like the writer 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.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
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 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
code-modernization
Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page…