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/rogerSuperBuilderAlpha/hult-cohort-programWrote 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/rules/rogersuperbuilderalpha/hult-cohort-program/cohort-platform)<a href="https://agentmods.dev/rules/rogersuperbuilderalpha/hult-cohort-program/cohort-platform"><img src="https://agentmods.dev/badge/rules/rogersuperbuilderalpha/hult-cohort-program/cohort-platform.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00370 |
| Opus 5 | $0.00000 | $0.00185 |
| Sonnet 5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
cohort-platform 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 8d 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
Cohort platform (Next.js)
Full guide: execution/marketing/site/AGENTS.md
Stack
Next.js 15 App Router · Firebase Auth (GitHub) · firebase-admin in API routes only · CSS modules (app/page.module.css)
Critical split
// ✅ Client component — types/format only
import type { CohortStats } from '@/lib/cohort-stats-types';
// ❌ Never in 'use client' files
import { getCohortStats } from '@/lib/cohort-stats-server';
Peer review (implemented)
- Written review: GitHub issue
Review by @{voter}: @{reviewee}(discovered viafetchContestState) - Optional upvote:
Vote: upin that issue body (or abstain — no downvotes) - UI: collapsed accordion in
PeerReviewCard.tsx— personal status only; refresh after filing - Staff tally (post review week):
npx tsx scripts/tally-votes.ts --project=<slug>
Program text
Edit content/program.ts; personalize with personalizeProgramText() for {peerCount}, {org}, {handle}.
Branding
Hult 2025 web palette in app/globals.css: cream #fffae7, magenta #cc164c, ink #2b2b2b, EF Circular + Libre Baskerville.
Env
Copy .env.example → .env.local. Service account at secrets/ (gitignored).
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.
- 8d ago First seen · 43 lines · 0 tokens per session scan A 89da3427f877
cohort-platform is a cursor rule published in the GitHub repository rogerSuperBuilderAlpha/hult-cohort-program (4 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 370 tokens. 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 cursor rules, from other repositories
frontend-development
Most coagents examples have a ui/ folder with Next.js applications.
examples-and-demos
Multi-agent systems with complex workflows.
suggestions-development
When working with suggesitons, always load this up.
agent-development
Python agents are typically in folders named agent-py/ or agent/ and use the sdk-python/ package.
development-workflow
CopilotKit uses a monorepo structure with.
quick-reference
Cursor rule "quick-reference" from CopilotKit/CopilotKit, covering copilotkit quick reference, need to...?, build a simple copilot, create multi-agent systems and integrate with crewai.