Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rajitsaha/100xprismnpx agentmods add rules/rajitsaha/100xprism/securityWrote 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/security)<a href="https://agentmods.dev/rules/rajitsaha/100xprism/security"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/security/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/rules/rajitsaha/100xprism/security"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/security.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 | $0.00005 | $0.01106 |
| Opus 5 | $0.00003 | $0.00553 |
| Sonnet 5 | $0.00001 | $0.00221 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade A, and why
security scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
. | grep -v node_modules | grep -v venv | grep -v dist | grep -v ".claude/" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suggested model tier: balanced (moderate reasoning)
Security — Vulnerability Scanner & Secret Audit
You are a security engineer. Auto-detect package managers, scan for vulnerabilities and leaked secrets, fix what's fixable, report the rest.
Do NOT ask for permission — scan everything, fix what you can, report the rest.
Step 1 — Detect package managers
PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
ls package.json api/package.json requirements.txt pyproject.toml 2>/dev/null
Step 2 — Load project-specific known exceptions
Read the project instruction file for any documented known exceptions before determining what is blocking:
# Detect project instruction file
INSTRUCTION_FILE=$(for f in CLAUDE.md AGENTS.md .cursorrules; do [ -f "$PROJECT_ROOT/$f" ] && echo "$PROJECT_ROOT/$f" && break; done)
[ -n "$INSTRUCTION_FILE" ] && grep -A3 -i "known exception\|security exception\|audit exception" "$INSTRUCTION_FILE" 2>/dev/null | head -30
In addition, the following patterns are universally non-blocking across all projects (install-time only, not runtime risks):
tar,node-gyp,@mapbox/node-pre-gyp,cacache,make-fetch-happen— native addon compilation duringnpm installundicivia Firebase SDK when fix requires--force(breaks Vite/other deps)sqlite3install-time compilation deps
Any high/critical vulnerability NOT matching the above patterns → BLOCKING.
Step 3 — Dependency vulnerability scan
npm projects:
# Root (frontend)
npm audit --json 2>/dev/null
# Backend (if api/ exists)
cd api && npm audit --json 2>/dev/null
Build severity summary per project:
| Project | Critical | High | Moderate | Low | Total |
|---|
Detail each critical/high: package, severity, advisory title, fix available, dependency chain, exception status.
Python projects:
./venv/bin/pip-audit 2>/dev/null || (./venv/bin/pip install pip-audit && ./venv/bin/pip-audit)
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.
- 5d ago First seen · 139 lines · 5 tokens per session scan A c497935b2b83
security is a cursor rule published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 8d ago), licensed MIT. It adds 5 tokens to every session and 1,106 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.