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.
npx skills add The-Utopia-Studio/skills --skill role-switchgit clone --depth 1 https://github.com/The-Utopia-Studio/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/skills/the-utopia-studio/skills/role-switch)<a href="https://agentmods.dev/skills/the-utopia-studio/skills/role-switch"><img src="https://agentmods.dev/badge/skills/the-utopia-studio/skills/role-switch/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/skills/the-utopia-studio/skills/role-switch"><img src="https://agentmods.dev/badge/skills/the-utopia-studio/skills/role-switch.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 | $0.00088 | $0.02050 |
| Opus 5.5 | $0.00035 | $0.00820 |
| Sonnet 5.5 | $0.00018 | $0.00410 |
| Haiku 4.5 | $0.00009 | $0.00205 |
Grade A, and why
role-switch 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Switch
Table of Contents
Workflow
Copy this checklist and track your progress:
Role Switch Progress:
- [ ] Step 1: Frame the decision or situation
- [ ] Step 2: Select relevant roles
- [ ] Step 3: Inhabit each role's perspective
- [ ] Step 4: Surface tensions and tradeoffs
- [ ] Step 5: Synthesize alignment and path forward
Step 1: Frame the decision or situation
Clarify what's being decided, key constraints (time, budget, scope), and why alignment matters. See Common Patterns for decision framing by type.
Step 2: Select relevant roles
Choose 3-6 roles with different goals, incentives, or constraints. See Role Selection Patterns for stakeholder mapping. For complex multi-stakeholder decisions → Study resources/methodology.md for RACI + power-interest analysis.
Step 3: Inhabit each role's perspective
For each role, articulate: what they optimize for, what they fear, how they measure success, what constraints they face. Use resources/template.md for structured analysis. For realistic roleplay → See resources/methodology.md for cognitive empathy techniques.
Step 4: Surface tensions and tradeoffs
Identify where perspectives conflict, map incompatible goals, articulate explicit tradeoffs. See Synthesis Principles for tension analysis.
Step 5: Synthesize alignment and path forward
Find common ground, propose resolutions that address core concerns, sequence decisions to build momentum. Self-check using resources/evaluators/rubric_role_switch.json. Minimum standard: Average score ≥ 3.5.
Role Selection Patterns
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 162 lines · 88 tokens per session scan A feda9fa1649b
role-switch is a skill published in the GitHub repository The-Utopia-Studio/skills (7 stars, last pushed 12d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,050 once invoked, about $0.0004 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 2026-08-31.
role-switch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| role-switchThe-Utopia-Studio/skills | Skill | 7 | 12d ago | Apache-2.0 | A | 88 | Claude Code |
| githubkostja94/marketing-skills | Skill | 1.1k | today | MIT | A | 165 | Claude Code, Codex |
| xml-sitemapkostja94/marketing-skills | Skill | 1.1k | today | MIT | A | 91 | Claude Code, Codex |
| google-adskostja94/marketing-skills | Skill | 1.1k | today | MIT | A | 95 | Claude Code, Codex |
| content-strategykostja94/marketing-skills | Skill | 1.1k | today | MIT | A | 95 | Claude Code, Codex |
| robots-txtkostja94/marketing-skills | Skill | 1.1k | today | MIT | A | 91 | Claude Code, Codex |
| heading-structurekostja94/marketing-skills | Skill | 1.1k | today | MIT | A | 57 | Claude Code, Codex |