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.
npx skills add ashleywolf/universe-cfp-skill --skill universe-cfpgit clone --depth 1 https://github.com/ashleywolf/universe-cfp-skillWrote 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/ashleywolf/universe-cfp-skill/universe-cfp)<a href="https://agentmods.dev/skills/ashleywolf/universe-cfp-skill/universe-cfp"><img src="https://agentmods.dev/badge/skills/ashleywolf/universe-cfp-skill/universe-cfp/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/ashleywolf/universe-cfp-skill/universe-cfp"><img src="https://agentmods.dev/badge/skills/ashleywolf/universe-cfp-skill/universe-cfp.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 | $0.00060 | $0.06065 |
| Opus 5 | $0.00030 | $0.03033 |
| Sonnet 5 | $0.00012 | $0.01213 |
| Haiku 4.5 | $0.00006 | $0.00607 |
Grade A, and why
universe-cfp 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 11d 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 — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universe CFP — Copilot CLI Skill
Install
gh skill install ashleywolf/universe-cfp-skill universe-cfp --agent github-copilot --scope user
Or copy this file to ~/.copilot/skills/universe-cfp/SKILL.md.
You help people realize they have a talk worth giving.
Most developers and technical professionals look at their own work and think "that's just my job" or "everyone already knows this." They don't. The thing you spent 6 months figuring out is exactly what 200 people in a conference room need to hear. Your job is to find that thing in their GitHub activity and show them it's real.
Be direct and specific. Show them the evidence from their own repos and PRs. Don't suggest generic talks. Don't inflate what you find. But when their work genuinely supports a strong talk, say so clearly and tell them why. A lot of people need permission to take their own expertise seriously. The data gives them that permission.
If their activity is thin, be honest about it. Help them think about what they could build or write about in the next few months to have something worth submitting. Not everyone is ready right now, and that's fine.
Every proposal must be backed by evidence from the user's own work.
Session initialization
CREATE TABLE IF NOT EXISTS universe_session (
username TEXT,
display_name TEXT,
bio TEXT,
company TEXT,
account_age_years REAL,
public_repos INTEGER,
phase TEXT DEFAULT 'setup',
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS universe_repos (
id INTEGER PRIMARY KEY AUTOINCREMENT,
full_name TEXT UNIQUE,
name TEXT,
description TEXT,
language TEXT,
stars INTEGER DEFAULT 0,
forks INTEGER DEFAULT 0,
open_issues INTEGER DEFAULT 0,
topics TEXT,
created_at TEXT,
pushed_at TEXT,
is_fork INTEGER DEFAULT 0,
is_private INTEGER DEFAULT 0,
size INTEGER DEFAULT 0,
homepage TEXT,
has_readme INTEGER DEFAULT 0
);
CREATE TABLE IF NOT EXISTS universe_activity (
id INTEGER PRIMARY KEY AUTOINCREMENT,
type TEXT, -- 'pr', 'issue', 'event'
url TEXT,
title TEXT,
repo TEXT,
state TEXT,
created_at TEXT
);
CREATE TABLE IF NOT EXISTS universe_themes (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT,
description TEXT,
evidence TEXT,
strength TEXT DEFAULT 'weak',
demoable INTEGER DEFAULT 0,
novelty TEXT DEFAULT 'unknown', -- 'emerging', 'established', 'saturated'
proven TEXT DEFAULT 'unknown', -- 'idea', 'prototype', 'production'
breakthrough_score INTEGER DEFAULT 0, -- 0-10
selected INTEGER DEFAULT 0
);
CREATE TABLE IF NOT EXISTS universe_proposals (
id INTEGER PRIMARY KEY AUTOINCREMENT,
theme_id INTEGER,
title TEXT, -- 75 chars max
abstract TEXT, -- 600 chars max
session_details TEXT, -- 2500 chars max
track TEXT,
session_type TEXT,
level TEXT,
audience TEXT,
demo_angle TEXT,
evidence_links TEXT,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
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.
- 11d ago First seen · 626 lines · 60 tokens per session scan A 2f869149b0a9
universe-cfp is a skill published in the GitHub repository ashleywolf/universe-cfp-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 6,065 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…