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 agentmods add rules/rajitsaha/100xprism/connectgit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/rajitsaha/100xprism/connect)<a href="https://agentmods.dev/rules/rajitsaha/100xprism/connect"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/connect.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 | $0.00011 | $0.07257 |
| Opus 5 | $0.00005 | $0.03629 |
| Sonnet 5 | $0.00002 | $0.01451 |
| Haiku 4.5 | $0.00001 | $0.00726 |
Grade B, and why
connect scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.pypirc Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -u "${JIRA_USER_EMAIL}:${JIRA_API_TOKEN}" \ How it starts
The opening of the file, as written. The whole thing — 892 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suggested model tier: fast / low-cost (mechanical task)
Connect — SaaS CLI Connection Manager
Usage
/connect # status dashboard — all services
/connect <service> # install + authenticate + test one service
/connect <service> test # test existing auth only (no re-auth)
Supported services: github · aws · gcp · azure · vercel · netlify · railway · heroku · flyio · supabase · planetscale · firebase · stripe · cloudflare · docker · terraform · sentry · datadog · jira · linear · slack · notion · npm · pypi · digitalocean · render · mongodb
Do NOT ask for permission. Do NOT print credential values. Do NOT skip checks.
Phase 0 — Bootstrap
PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD")
ENV_FILE="$PROJECT_ROOT/.env"
# Load .env if it exists
if [ -f "$ENV_FILE" ]; then
set -a; source "$ENV_FILE"; set +a
echo ".env loaded from $ENV_FILE"
else
echo "No .env found at $ENV_FILE"
echo "→ Copy .env.example to .env and fill in your credentials:"
echo " cp .env.example .env && \$EDITOR .env"
fi
Detect SERVICE from the argument (e.g. /connect github → SERVICE=github). If no argument, run Phase 3 (status dashboard) for ALL services.
Phase 1 — Helper functions (reference, do not run)
These patterns are used in each service section below.
# Check if a CLI is installed
check_cli() { command -v "$1" &>/dev/null && echo "✅ $1 installed" || echo "❌ $1 not found"; }
# Check if an env var is set (no value printed)
check_env() { [ -n "${!1}" ] && echo "✅ $1 set" || echo "❌ $1 missing — add to .env"; }
# Install via Homebrew
brew_install() { brew install "$1" && echo "✅ $1 installed" || echo "❌ install failed"; }
Phase 2 — Service sections
Run ONLY the section matching the requested SERVICE.
SERVICE: github
Required env vars: GITHUB_TOKEN
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.
- yesterday First seen · 892 lines · 11 tokens per session scan B e4655e68f75b
connect is a cursor rule published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 7,257 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.