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 commands/ainsteinsbr/renata/personagit clone --depth 1 https://github.com/AInsteinsBR/renataWrote 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/commands/ainsteinsbr/renata/persona)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/persona"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/persona.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00923 |
| Opus 5 | $0.00011 | $0.00462 |
| Sonnet 5 | $0.00004 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
persona 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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:persona — Extract a structured persona
You are a product researcher. You receive a name/role in $ARGUMENTS and extract a structured persona, adding it to docs/business-context/personas.md.
Respond to the user and generate document content in the user's language (the language they are writing in).
Before generating
-
Read
@CLAUDE.mdfor the product context. -
If
docs/discovery/*.mdexists, read the "Persona candidate" seed as a starting draft — but still formalize the full persona here (name, quantified pain, anchor phrase, anti-persona). The seed is a starting point, not a substitute. -
Check whether the persona already exists in
docs/business-context/personas.md. If so, refine it. -
Ask in up to 4 turns (not all at once):
Turn 1 — Role and context:
- What position does this person hold? In what type of company? What size?
- What is their routine?
Turn 2 — Specific pain:
- What is their pain with a number (hours, %, R$, frequency)?
- What have they already tried to solve it? Why did it fail?
Turn 3 — Success criterion:
- In their words: "When will I know I've won?"
- What would their anchor phrase about the problem be?
Turn 4 — Anti-persona:
- Who is NOT this persona? Who looks like them but isn't?
Quality rules
- ❌ A persona without a proper name → require one ("Marina", not "EM").
- ❌ A pain without a number → require one. "Wastes time" is a wish; "loses 6h/week" is a pain.
- ❌ No "what they already tried" → require it. A history of failed attempts is gold.
- ❌ No anti-persona → require one. Defining who it is not avoids fuzzy scope.
Structure
Each persona has 2 quotation blocks that serve different purposes — don't confuse them:
- Success criterion → a longer, descriptive sentence. It answers "when will I know I've won?". The persona describing the victory.
- Anchor phrase → a short, impactful motto (1 line). It answers "what is the battle cry of the pain?". It will become the team's mantra.
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.
- 6d ago First seen · 93 lines · 22 tokens per session scan A 1830e68e14f4
persona is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 15d ago), licensed MIT. It adds 22 tokens to every session and 923 once invoked, about $0.0001 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 commands, from other repositories
recipe-blueprint
Define the structural design context needed by a prototype or PRD.
recipe-define
Create a PRD from validated product decisions and evidence.
recipe-discover
Frame product opportunities and create decision-relevant hypotheses.
recipe-persona
Create or update evidence-backed personas for product decisions.
recipe-prototype-prompt
Export an evidence-grounded prompt for an external prototype generator.
recipe-refine-visuals
Refine the auto-derived Visual Tokens with a design-capable human.