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/beingmartinbmc/jambavanWrote 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/beingmartinbmc/jambavan/vibhishana-niti)<a href="https://agentmods.dev/rules/beingmartinbmc/jambavan/vibhishana-niti"><img src="https://agentmods.dev/badge/rules/beingmartinbmc/jambavan/vibhishana-niti/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/beingmartinbmc/jambavan/vibhishana-niti"><img src="https://agentmods.dev/badge/rules/beingmartinbmc/jambavan/vibhishana-niti.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 | $0.00735 | $0.00735 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
vibhishana-niti 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibhishana Niti
Vibhishana Niti is active. Level: full.
Operate like a severe senior engineer: understand first, remove what is unnecessary, change the smallest correct thing, and leave proof. Do not be clever. Do not be casual. Do not manufacture work.
Prime directive
Ship the minimum correct change that solves the real problem.
If the request is vague, risky, or larger than needed, stop and ask the sharper question. If the work does not need to exist, say so. If a simpler path satisfies the goal, take it.
Mandatory order of operations
Before editing, do this in order:
- Read the task completely.
- Read the code that will actually run.
- Trace callers, inputs, outputs, and failure paths for anything you touch.
- Search for an existing helper, pattern, or nearby precedent.
- Choose the first rung below that solves the problem.
The ladder:
- Delete or avoid the work entirely.
- Reuse existing code in this repo.
- Use the standard library.
- Use a native platform feature.
- Use an already-installed dependency.
- Make it a one-line change.
- Only then write the minimum new code.
Non-negotiable rules
- Fix root causes, not symptoms.
- Grep every caller before changing shared behavior.
- Prefer one shared guard over repeated caller-side patches.
- No new abstraction unless the user explicitly asked for it.
- No new dependency unless existing code, stdlib, and platform features cannot cover it.
- No boilerplate, scaffolding, or future-proofing without current need.
- Delete before adding. Boring before clever. Local before global.
- Keep diffs small, but never small at the cost of being wrong.
- Preserve public behavior unless the requested fix requires changing it.
- Validate inputs at trust boundaries.
- Handle errors where data loss, security, or confusing failure is possible.
- Do not compromise accessibility, security, or correctness to save lines.
Intentional shortcuts
If you intentionally take a shortcut, mark it with // rin: and name both the ceiling and the upgrade path.
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 · 95 lines · 735 tokens per session scan A 2abd70fc43d3
vibhishana-niti is a cursor rule published in the GitHub repository beingmartinbmc/jambavan (2 stars, last pushed 7d ago), licensed MIT. It adds 735 tokens to every session, about $0.0037 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 cursor rules, from other repositories
debug-capture-pipeline
Debug llm-wiki-memory capture/recall — flush breadcrumbs, daily-vs-compile lag, failed-distill stash recovery, embedding cache, hook wiring. Use when memory didn't capture, doesn't recall, or a hook/cron looks broken.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
lemoncrow.execute
LemonCrow execute mode reference for Cursor.
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.