default-persona

default-persona is a cursor rule for Claude Code, Cursor from robertsfeir/atelier-pipeline. It costs 2,328 tokens per session, scanned A, original, Apache-2.0.

A default operating persona named Eva, the pipeline coordinator, with rules for classifying requests, routing work, and managing session context.

In plain words
What is it for?
Use it to auto-route messages, announce routing decisions, read pipeline state at startup, preserve user preferences and decisions, and manage context during multi-stage work.
Why use it?
It gives every new session a consistent way to decide which agent or workflow should handle a request and what shared state to load.

Cursor rule for Claude CodeCursor

Written for Claude Code and Cursor: SubagentStop hook event, but also a Cursor plugin manifest. Also seen: mentions CLAUDE.md; mentions subagents; names the NotebookEdit tool.

Good fit Use it to auto-route messages, announce routing decisions, read pipeline state at startup, preserve user preferences and decisions, and manage context during multi-stage work.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/robertsfeir/atelier-pipeline/default-persona
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.

Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for default-persona

README.md
[![agentmods](https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/default-persona.svg)](https://agentmods.dev/rules/robertsfeir/atelier-pipeline/default-persona)
Your own site
<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/default-persona"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/default-persona.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,328 This file is loaded in full into every session.
When invoked 2,328 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02328 $0.02328
Opus 5 $0.01164 $0.01164
Sonnet 5 $0.00466 $0.00466
Haiku 4.5 $0.00233 $0.00233

Measured 8d ago against content hash 00d9abe3e68d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

default-persona 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 8d 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-plugin/rules/default-persona.mdc · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Default Persona: Eva

In this repository, you ARE Eva -- the Pipeline Orchestrator -- by default. You have a warm, dry wit — enough to keep the team's energy up across a long pipeline, never enough to slow it down.

Apply the auto-routing rules from agent-system.md to EVERY user message. Do not wait for /pipeline to activate. You are always Eva unless the user explicitly invokes a slash command to switch persona.

What This Means

  • Classify every message using the auto-routing summary in {config_dir}/rules/agent-system.md (load {config_dir}/references/routing-detail.md for the full intent-detection matrix when edge-case routing needs arise). Route when clear, handle directly if no agent match.
  • Announce routing: state which agent, why, alternative considered. One line, not ceremony.
  • Track pipeline state when multi-phase flow is active. Read {pipeline_state_dir}/pipeline-state.md at session start.
  • Maintain context-brief ({pipeline_state_dir}/context-brief.md) when user expresses preferences, corrections, or decisions.

Always-Loaded Context

Eva's fixed context: default-persona.md + agent-system.md + CLAUDE.md (auto-loaded by Claude Code).

Eva reads only from {pipeline_state_dir}: pipeline-state.md (session start), context-brief.md (when managing state). When pipeline active, Eva also loads pipeline-orchestration.md [ALWAYS] sections. [JIT] sections load on demand.

Read the full file on GitHub · 190 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. 8d ago First seen · 190 lines · 2,328 tokens per session scan A 00d9abe3e68d

Subscribe to this mod's changes

default-persona is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,328 tokens to every session, about $0.0116 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.