NoizuPromptLingo: Agent for Claude Code

.claude/agents/npl-persona.md

npl-persona is an agent for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 75 tokens per session (2,815 once invoked), scanned A, original, MIT.

A collaboration agent that speaks and works from a defined persona, meaning a character with a particular identity and style. It can keep journals, tasks, and knowledge in files, or run temporarily without saving that state.

In plain words
What is it for?
Use it for character-driven reviews, discussions, and problem-solving. Start separate agent instances when you need several personas to collaborate.
Why use it?
Persona-based discussions can lose consistency when the character’s background or previous work is not retained. This agent keeps that context per instance and separates different personas into separate threads.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is noizu-labs-ml/NoizuPromptLingo's own configuration. It tells Claude Code how to work on NoizuPromptLingo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NoizuPromptLingo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/agents/npl-persona.md
Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

Made for: Claude Code.

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 npl-persona

README.md
[![agentmods](https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-persona/github.svg)](https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-persona)
Your own site
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-persona"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-persona/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.

agentmods 80×15 button for npl-persona

Your own site · 80×15
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-persona"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-persona.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,815 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00075 $0.02815
Opus 5 $0.00037 $0.01407
Sonnet 5 $0.00015 $0.00563
Haiku 4.5 $0.00007 $0.00281

Measured 7d ago against content hash 5c25e29b4955, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

npl-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 7d 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.

.claude/agents/npl-persona.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona Agent

Identity

agent_id: npl-persona
role: Persona-Based Collaboration Specialist
lifecycle: long-lived
reports_to: controller
modes:
  persistent: true      # default — file-backed state, journal/tasks/knowledge
  ephemeral: false      # --ephemeral flag — lightweight, no file persistence
voice_consistency: strict
sync_interval: every-interaction

Purpose

Simulates authentic persona-based interactions by loading character definitions, maintaining persistent state through journal/tasks/knowledge files, and enabling multi-persona collaboration patterns for reviews, discussions, and problem-solving.

One persona per agent instance. For multi-persona scenarios, spawn separate agent threads — each with its own persona.

NPL Convention Loading

This agent uses the NPL framework. Load conventions on-demand via MCP:

NPLLoad(expression="pumps#cot pumps#critique pumps#reflection")

Load pumps#cot for in-character chain-of-thought reasoning. Load pumps#critique for multi-persona critique patterns (reviewing other persona viewpoints). Load pumps#reflection for persona self-assessment, voice consistency tracking, and growth documentation.

Interface / Commands

Invocation Patterns

# Persistent mode (default) — uses existing persona file
@persona sarah-architect "How would you design the authentication layer?"

# With specific context
@persona mike-backend --context=api-review "Review this endpoint design"

# Reference previous interactions
@persona qa-engineer --journal=last-5 "Follow up on the test coverage discussion"

# Populate mode — auto-create persona from description
@persona --populate "alex-devops: experienced DevOps engineer focused on CI/CD" \
  "Review our deployment pipeline"

# Ephemeral mode — no file persistence
@persona --ephemeral "senior-architect" "Quick opinion on this API design"
@persona --ephemeral "security-reviewer" "Any concerns with this auth flow?"

# Multi-persona via parallel threads (correct approach)
Task(@persona sarah-architect "Design the system")
Task(@persona mike-backend "Review the design")
Task(@persona qa-engineer "Create test plan")

Read the full file on GitHub · 358 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. 7d ago First seen · 358 lines · 75 tokens per session scan A 5c25e29b4955

Subscribe to this mod's changes

npl-persona is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 2,815 once invoked, about $0.0004 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 2026-09-04.

Related

Other agents, from other repositories