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 agentmods add skills/viktorbezdek/skillstack/custom-personasnpx skills add viktorbezdek/skillstack --skill custom-personasgit clone --depth 1 https://github.com/viktorbezdek/skillstackWhat 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 | $0.00175 | $0.02708 |
| Opus 5 | $0.00088 | $0.01354 |
| Sonnet 5 | $0.00035 | $0.00542 |
| Haiku 4.5 | $0.00017 | $0.00271 |
Grade A, and why
custom-personas 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 3d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom Personas
The canonical 12 cover most decisions. They don't cover every domain. When you need a CFO for a budget brainstorm or a security engineer for threat modeling, design the persona — don't force a canonical to fit.
This skill covers the design discipline for ad-hoc personas: when a custom is justified, how to write the persona prompt, how to invoke it inline (without shipping a new subagent file).
Core principle
A custom persona is a tool, not a feature. Design one when the canonical 12 demonstrably don't cover the domain. Don't design custom personas to "be thorough" or to feel comprehensive — that produces sock-puppet personas that contribute generic content.
When a custom persona is justified
A custom persona is justified when:
- The domain has specialized knowledge that the canonical personas don't have (e.g. tax law, regulatory compliance, hardware reliability, biotech)
- The decision affects a specific stakeholder group with a distinct perspective (e.g. enterprise procurement, customer success at scale, sales at a specific deal size)
- The framing requires expertise the canonical personas wouldn't bring (e.g. economist for pricing strategy, behavioral psychologist for engagement design)
- The brainstorm is industry-specific (e.g. healthcare, finance, defense, EdTech)
A custom persona is NOT justified when:
- The canonical personas would cover it adequately if you tightened their prompts
- You're trying to "represent everyone" — the swarm is illustrative, not exhaustive
- You want a "voice" persona (poet, philosopher, etc.) that doesn't carry domain expertise
- The custom persona's contribution would substantially overlap with a canonical one
Common custom persona archetypes
| Domain | Custom persona | What they bring |
|---|---|---|
| Budget / finance | CFO | ROI rigor, capital allocation framing, runway implications |
| Legal / compliance | General Counsel | regulatory risk, contract implications, IP concerns |
| Security | Security Engineer | threat modeling beyond what Operator covers, attack surface |
| Sales | Sales Lead | what closes deals, what blocks them, win/loss patterns |
| Customer Success | CS Lead | renewal risk, expansion opportunity, support burden |
| Marketing | Head of Marketing | positioning, launch strategy, channel implications |
| Data | Data Scientist | what's measurable, what data we have, what we can learn |
| HR / People | People Operations | culture impact, hiring implications, team dynamics |
| Industry-specific | [Domain] Expert | regulatory specifics, industry conventions, domain risks |
| Stakeholder voice | The [specific stakeholder] | the actual voice of an affected party (enterprise CTO, hospital admin, school principal) |
What ships with it
4 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.
- 3d ago First seen · 283 lines · 175 tokens per session scan A e5e3b89d40ba
custom-personas is a skill published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 175 tokens to every session and 2,708 once invoked, about $0.0009 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.
Other skills, from other repositories
gossipcat
Use when installing or setting up gossipcat multi-agent orchestration (parallel review, consensus, adaptive dispatch) in Claude Code or Cursor. Installs the gossipcat MCP server and hands off to gossipstatus() for all live rules.
Elephant Agent
Complete guide to what Elephant Agent is, how to use it from the CLI, how herd, wake, Personal Model, proactive curiosity, skills, and tools fit together, and how to explain Elephant Agent clearly to users, contributors, or evaluators.
libretranslate-markdown-i18n
Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…
awesome-skills-master
Master catalog orchestrator and autonomous installer for AI agents. Use when exploring, cloning, discovering, or installing skills, plugins, or MCP servers from awesome-skills without using interactive CLI tools. Guides environment detection, rule adaptation (.mdc/CLAUDE.md), MCP configuration, and strict author…
readme-template
Standard README template for repos — professional structure with badges, overview, table of contents, features/modules, stack, installation, configuration, tests, security, structure, docs, roadmap, contribute, license, author + RepoActivity sections (Star History, repo stats) + profile GIF footer. Use when creating…
suap-iff-api
Authenticate to and consume the SUAP IFF (Instituto Federal Fluminense) API v2 from the CLI — obtain the JWT access/refresh token via matricula+senha, then fetch student data (periodos letivos, dados do aluno, boletim). Use when the user has a suap.iff.edu.br matricula+senha and wants to extract academic data…