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/gateWrote 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/gate)<a href="https://agentmods.dev/rules/rajitsaha/100xprism/gate"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/gate/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/gate"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/gate.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 | $0.01600 | $0.01600 |
| Opus 5 | $0.00800 | $0.00800 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
gate 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 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.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gate — Pre-Commit Quality Gate
MANDATORY before every commit and push. Gates 1–3 always run; Gates 4 (Docker) and 5 (Cloud) only when applicable. Do NOT ask for permission, skip gates, or continue past a failure — if any gate fails: STOP, fix, re-run the gate.
How to run the gates (fan out the independent ones)
Gate 1 (the coverage loop) is the long pole — start it first and let it finish. Gates 2–5 (security, build, docker, cloud-security) are mutually independent, so run them in parallel using the fan-out ladder from the subagents skill: prefer the Workflow tool (one stage per gate, schema-validated return), else parallel Agent/Task subagents, else serial. Each gate subagent returns a structured verdict:
{ "gate": "security", "status": "passed|failed|skipped", "severity": "critical|high|none", "findings": ["..."] }
The parent reduces the verdicts into the summary below: any failed with critical/high severity ⇒ overall FAILED. Cache each verdict keyed on the tree hash (git write-tree + clean-tree check) — the same key the gate-pass.py token uses (see Record the pass) — so a re-run on an unchanged tree reuses the verdict. Never reuse a verdict across a changed tree.
Gate 1 — Test Coverage (≥ 95%)
Run the test workflow, ALL test layers (unit, integration, E2E if configured).
- Lines ≥ 95% | Functions ≥ 95% | Statements ≥ 95% | Branches ≥ 90%
- Zero failing tests
Gate 2 — Security (no critical, no high)
Run the security workflow across every package manager found in the project.
- Zero critical, zero high vulnerabilities; no real secrets in tracked files
- Known exceptions count only if explicitly documented in the project's
/securityoverride (e.g. install-time-only transitive deps); when in doubt, treat as blocking
Gate 3 — Local Build
Detect and run all applicable builds:
PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
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 · 140 lines · 1,600 tokens per session scan A 5a9fc0d53172
gate is a cursor rule published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 8d ago), licensed MIT. It adds 1,600 tokens to every session, about $0.0080 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 2026-09-03.
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.