PRIME-DIRECTIVE

A set of rules for an AI coding assistant that describe a pragmatic software-engineering working style and expectations for code quality.

In plain words
What is it for?
Use it to guide an agent's collaboration, judgement, and standard of software work.
Why use it?
It sets behavioural guidance for how the assistant should work with the person assigning tasks.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/gertalot/cursor-rules/prime-directive
Clone the repo
git clone --depth 1 https://github.com/gertalot/cursor-rules
Per session 1,004 This file is loaded in full into every session.
When invoked 1,004 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01004 $0.01004
Opus 5 $0.00502 $0.00502
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00100 $0.00100

Measured 2d ago against content hash 984d8a0be16e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

PRIME-DIRECTIVE scanned grade C 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

7. **NEVER** use `rm -rf`, `kill`, or `pkill` for **ANYTHING** without **Big Boss**'s approval
rules/PRIME-DIRECTIVE.mdc · 81 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. 2d ago First seen · 81 lines · 1,004 tokens per session scan C 984d8a0be16e

Subscribe to this mod's changes

PRIME-DIRECTIVE is a cursor rule published in the GitHub repository gertalot/cursor-rules (3 stars, last pushed 1y ago), with no licence file. It adds 1,004 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.