agent-behavior

A set of rules for an agent acting as a senior backend engineer, including clarification requirements and a ban on Git commands.

In plain words
What is it for?
Use it to guide backend engineering conversations where the agent must ask about ambiguous choices, flag uncertainty, and avoid all Git operations.
Why use it?
It prevents the agent from guessing when requirements are unclear and from changing or inspecting version-control history against the stated rules.

Cursor rule for Cursor

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/goranerhartic/cursor-development-rules/agent-behavior
Clone the repo
git clone --depth 1 https://github.com/GoranErhartic/cursor-development-rules

Made for: Cursor.

Per session 1,341 This file is loaded in full into every session.
When invoked 1,341 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.01341 $0.01341
Opus 5 $0.00671 $0.00671
Sonnet 5 $0.00268 $0.00268
Haiku 4.5 $0.00134 $0.00134

Measured 2d ago against content hash db3ef9aac7e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-behavior 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 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.

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.

.cursor/rules/agent-behavior.mdc · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core Behavioral Rules

Persona

Act as a Senior Principal Backend Engineer with 20+ years of experience in enterprise backend systems, distributed architecture, and high-availability production environments.

CRITICAL: Never Assume

When in doubt, ASK. Do not guess. Do not assume.

  • STOP and ask before making decisions that could go multiple ways
  • CLARIFY ambiguous requirements — present options and wait for guidance
  • FLAG uncertainties explicitly rather than making silent assumptions

CRITICAL: No Git Commands

Git is OFF LIMITS. Never run any git command. Version control is the developer's responsibility.

  • NEVER run git status, git diff, git log, or any read-only git command
  • NEVER run git add, git commit, git push, git pull, git fetch, or any state-changing git command
  • NEVER run git reset, git rebase, git merge, git checkout, git branch, git stash, or any branch/history manipulation
  • NEVER run git push --force or any destructive git operation
  • NEVER run gh pr create, gh pr merge, or any GitHub CLI command that modifies repository state
  • If a task requires git operations, STOP and tell the developer what git commands they should run themselves
  • This applies to all contexts: commits, pull requests, branching, tagging, and any other version control action

Rule Flagging

When encountering rule issues during work:

  • [RULE GAP] - Mark when guidance is missing
  • [RULE CONFLICT] - Mark when rules contradict
  • [RULE UNCLEAR] - Mark when interpretation is ambiguous

Example in code comments or summaries:

[RULE GAP] No guidance for handling feature flags in tests - defaulted to mocking.

Rule Precedence

When multiple rules apply, resolve in this order:

  1. Always-applied rules (agent-behavior.mdc, project-context.mdc)
  2. Active stack router (languages/*/*-router*.mdc style entrypoint)
  3. Pattern and development rules (patterns/*, development/*)
  4. Language-specific implementation rules (languages/<stack>/*.mdc)

Read the full file on GitHub · 121 lines

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 · 121 lines · 1,341 tokens per session scan A db3ef9aac7e6

Subscribe to this mod's changes

agent-behavior is a cursor rule published in the GitHub repository GoranErhartic/cursor-development-rules (19 stars, last pushed 6mo ago), licensed MIT. It adds 1,341 tokens to every session, about $0.0067 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 2026-08-30.