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 joymin5655/Agent --skill persona-reviewgit clone --depth 1 https://github.com/joymin5655/AgentWrote 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/joymin5655/agent/persona-review)<a href="https://agentmods.dev/skills/joymin5655/agent/persona-review"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/persona-review/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/joymin5655/agent/persona-review"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/persona-review.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 | $0.00097 | $0.01703 |
| Opus 5 | $0.00048 | $0.00851 |
| Sonnet 5 | $0.00019 | $0.00341 |
| Haiku 4.5 | $0.00010 | $0.00170 |
Grade A, and why
persona-review 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 10d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/persona-review
Goal
Answer one question with evidence from a diverse panel of ordinary users: how would real people react to this? You seat five synthetic-but-grounded Korean personas — sampled from Korean census distributions — in front of a target artifact and report their reactions, frictions, and what to change.
This is a citizen/user lens: comprehension, trust, tone, and clarity. It
stands beside code-reviewer (correctness) and security-reviewer
(vulnerabilities) and replaces neither. A panelist may voice a worry that is
really a security or correctness concern ("is my data safe here?") — capture it
as a user worry and route it to the right reviewer; do not adjudicate it here.
Leading word: panel. Five independent voices, then one synthesis — not one voice pretending to be five.
Inputs
- Target — the artifact under review: a URL, a file path, pasted copy, a screenshot description, or a component. Required.
- Question (optional) — what to probe: first-read comprehension, trust, tone, call-to-action clarity, pricing legibility. Default when unstated: first-time-visitor comprehension + trust.
- Catalog —
skills/persona-review/personas/catalog.json(shipped). If it is missing or unparseable, stop and say so — do not invent personas.
Steps
1. Load the catalog
Read skills/persona-review/personas/catalog.json and confirm
personas is a non-empty list. Each entry carries age, sex, province,
occupation, education_level, a one-line summary, hobbies / skills,
and a review_lens tag (1-2 of UX / 카피 / 접근성 / 신뢰 / 가격민감 —
what kind of scrutiny this panelist is naturally suited to).
Completion criterion: you can name the persona count and it is > 0.
2. Frame the target
State, in one line each: what the artifact is, and which question the panel answers. If the caller gave only "review this", use the default question. If the target is a URL or file you can open, open it first so panelists react to real content, not a guess.
What ships with it
2 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.
- 10d ago First seen · 146 lines · 97 tokens per session scan A 2a74874035f6
persona-review is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed 8d ago), licensed MIT. It adds 97 tokens to every session and 1,703 once invoked, about $0.0005 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.
Other skills, from other repositories
use-show-pages
Build, inspect, update, restore, or share Avibe Show Pages for visual explanations, diagrams, reports, or interactive prototypes. Covers the page workspace and its Git history.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
infographic-creator
An information-graphic creation guide that turns written information into a visual layout using AntV Infographic, a description language for rendering infographics.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
visual-design
A design skill for turning content into complete, self-contained HTML pages and visual materials such as websites, banners, posters, reports, resumes, and portfolios. It follows a defined visual design system and does not use outside images or code libraries.