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/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/agent-persona-design)<a href="https://agentmods.dev/rules/j4flmao/agent-skills/agent-persona-design"><img src="https://agentmods.dev/badge/rules/j4flmao/agent-skills/agent-persona-design/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/j4flmao/agent-skills/agent-persona-design"><img src="https://agentmods.dev/badge/rules/j4flmao/agent-skills/agent-persona-design.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 | $0.00018 | $0.00375 |
| Opus 5.5 | $0.00007 | $0.00150 |
| Sonnet 5.5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
agent-persona-design 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 1mo 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.
What it actually says
Agent Persona Design & Orchestration
Cursor/AI MUST follow these rules when writing code for Multi-Agent systems (LangGraph, AutoGen, CrewAI).
1. The Anti-God Agent Rule
- Rule: Never create a single Agent loaded with more than 5 tools.
- Why: An LLM with too many tools suffers from "Tool Paralysis" and hallucination. If a workflow requires 15 tools, you MUST design a Multi-Agent system (e.g., a Supervisor routing to 3 specialized sub-agents).
2. Principle of Least Privilege
- Rule: Agents must only be granted the specific tools required for their narrow scope.
- Example: A
ReviewerAgentmust be granted aread_filetool, but MUST NOT be granted awrite_fileorexecute_codetool. Only theCoderAgentgets write access.
3. Enforce State Structuring (Blackboard)
- Rule: When defining the shared state (e.g.,
StateGraphin LangGraph), do not pass raw chat messages as the only state. You MUST define a rigid TypedDict/Pydantic schema representing the specific variables needed (e.g.,current_code,linter_errors,approval_status).
4. Destructive Action Checkpoints
- Rule: If an agent possesses a tool that modifies production state (e.g.,
execute_sql,deploy_to_aws,delete_file), you MUST implement a Human-in-the-loop (HITL) breakpoint (e.g.,interrupt_before=["deploy_node"]) before that node executes.
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.
- 1mo ago First seen · 23 lines · 18 tokens per session scan A 47027e992ad0
agent-persona-design is a cursor rule published in the GitHub repository j4flmao/agent-skills (33 stars, last pushed 10d ago), licensed MIT. It adds 18 tokens to every session and 375 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).