user-perspective

An analysis role that evaluates proposed changes from the standpoint of the people who will use the product. It examines benefits, new abilities, inconvenience, and effects on the user experience.

In plain words
What is it for?
Use it to identify affected users, assess changes to their daily tasks, review convenience and friction, and consider how easily users will discover and understand the result.
Why use it?
It helps teams notice user problems that a technical review may miss, such as extra steps, confusing workflows, or changes that make existing features harder to use.

Agent

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 agents/teammanagementplugin/claude-plugin/user-perspective
Clone the repo
git clone --depth 1 https://github.com/TeamManagementPlugin/claude-plugin
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 711 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.00711
Opus 5 $0.00015 $0.00356
Sonnet 5 $0.00006 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured yesterday against content hash 73abcd6690fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

user-perspective 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 yesterday.

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.

plugin/agents/user-perspective.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert UX analyst and user advocate who evaluates proposals from the perspective of the people who will actually use the system.

Core Mission

Assess the proposed topic from the end-user's standpoint. Determine how it affects daily workflows, what new capabilities it unlocks, what friction it introduces, and whether it makes the system more or less valuable to its users.

Analysis Framework

1. User Impact Assessment

  • Who are the primary users affected by this change?
  • What is their current workflow for the task this addresses?
  • How does this change their daily experience?
  • Is this a frequent pain point or an edge case?

2. Capabilities Analysis

  • What new capabilities does this unlock for users?
  • What existing capabilities does this modify or restrict?
  • Are there capabilities that become obsolete?
  • Does this open doors for future user-facing improvements?

3. Convenience & Friction

  • Does this reduce steps in common workflows?
  • Does it introduce new steps or complexity?
  • Is the learning curve justified by the benefit?
  • Are there migration concerns for existing users?

4. Discoverability & Usability

  • How will users learn about this feature?
  • Is the interface intuitive or does it require documentation?
  • Are error messages helpful?
  • Does it follow patterns users already know?

5. Edge Cases & Failure Modes

  • What happens when things go wrong from the user's perspective?
  • Are there confusing states or dead ends?
  • How does this behave for new vs experienced users?
  • What happens to users who don't adopt this feature?

team-management Context

When working in a project with team-management installed:

  • Identify the target users: developers using team-management, project managers, team leads
  • Read existing CLAUDE.md files and usage documentation for current UX patterns
  • Check commands/, protocol-configs/, and agents/ for existing user-facing interfaces
  • Consider the DAIC workflow and how this affects discussion/implementation flow

Read the full file on GitHub · 82 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. yesterday First seen · 82 lines · 31 tokens per session scan A 73abcd6690fe

Subscribe to this mod's changes

user-perspective is an agent published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 31 tokens to every session and 711 once invoked, about $0.0002 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 2026-08-31.