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 LuuOW/meridian-mcp --skill persona-researchgit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/luuow/meridian-mcp/persona-research)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/persona-research"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/persona-research/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/luuow/meridian-mcp/persona-research"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/persona-research.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 | $0.00051 | $0.00664 |
| Opus 5 | $0.00026 | $0.00332 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
persona-research 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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
persona-research
Use this when the task is to build a source base for a person-specific profile, partner agent, or high-fidelity voice model from public material.
Use It For
- Finding the right person across ambiguous search results
- Expanding from an official site into high-signal internal pages
- Ranking public sources by usefulness for persona modeling
- Separating self-authored material from reviews, testimonials, and commentary
Workflow
-
Start with seeded facts:
- official website
- known YouTube/channel URLs
- LinkedIn/X/Instagram/newsletter/podcast URLs
- domain keywords and exclude keywords
-
Discover candidate sources:
- search the person name alone
- search the person name with domain-specific terms
- search the official domain for bio, about, newsletter, podcast, articles, services
- search YouTube watch pages, not just channel pages
-
Score and keep sources in this priority order:
- official bio/about pages
- self-authored newsletters and articles
- direct video/podcast episode pages with transcript potential
- self-authored landing pages describing methods, products, or worldview
- secondary profiles like LinkedIn
-
De-prioritize or exclude:
- wrong-person matches
- generic channel pages
- widget-heavy social embeds
- testimonials and student/customer quotes
- pages dominated by site chrome rather than authored text
Source Quality Heuristics
- Prefer first-person language over third-party praise
- Prefer pages with concrete claims, methods, beliefs, and tradeoffs
- Prefer episode pages and transcripts over thumbnails, posts, or playlists
- Prefer stable identity pages for biography and claims
- Prefer public sources that can be cited later
Identity Collision Handling
When multiple people share the same name:
- add
focus_keywordstied to the target domain - add
exclude_keywordstied to the wrong identity - boost
preferred_domains - require at least one official domain or self-authored page before accepting a new cluster of sources
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.
- 11d ago First seen · 84 lines · 51 tokens per session scan A e8031649ff02
persona-research is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 664 once invoked, about $0.0003 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
zernio
Schedule posts, manage inbox, broadcasts, sequences, and automations across 14 platforms from the CLI.
beat-setup-guide
Generate a beat setup guide for a journalist starting a new coverage area: source map, document inventory, recurring calendar, key contacts, institutional landscape, and a 30-day ramp-up plan.
source-credibility-brief
Assesses the credibility of a source whose claims appear in a draft — expertise, track record, conflicts of interest, and the corroboration needed before publication.
target-audience-definer
Produces a clear, specific description of who a piece of content is written for — including what that audience already knows, what they care about, and what they will do with the information — so editors, writers, and distributors can make better decisions at every stage of production.
social-media-excerpt
Extracts and reformats the most shareable passage or argument from a published article into platform-specific social media posts — without rewriting the journalism.
source-research-brief
Produces a structured pre-interview research brief on a potential source, covering their professional background, public positions, known biases, potential conflicts of interest, and suggested lines of questioning.