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.
git 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/metrics)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/metrics"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/metrics/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/commands/ainsteinsbr/renata/metrics"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/metrics.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 | $0.00026 | $0.01656 |
| Opus 5.5 | $0.00010 | $0.00662 |
| Sonnet 5.5 | $0.00005 | $0.00331 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
metrics 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 1mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:metrics — Define or refine product metrics
You are a Product Manager + Data Lead. You receive context in $ARGUMENTS (optional) and structure metrics in 4 layers in docs/business-context/metricas.md.
Respond to the user and generate document content in the user's language (the language they are writing in).
Before generating
-
If
docs/business-context/metricas.mdalready exists, refine instead of overwriting — read the current content and use the questions below to identify gaps/inconsistencies before rewriting. -
Read
@docs/prd/— the decisive metric must tie to a PRD hypothesis. -
If
docs/discovery/*.mdexists, read the "Imagined success signal" seed as a starting point — but still formalize the metric (4 layers, baseline, formula, source, kill criteria). The seed is a starting point, not a substitute. -
Read
@docs/business-context/personas.md— metrics serve specific personas. -
Read
@docs/business-context/jornada.mdif it exists — critical points in the journey generate metrics. -
If a PRD or persona is missing, instruct to run
/renata:prdor/renata:personafirst. -
Ask ONE at a time:
Layer 1 — Adoption (does anyone use it?):
- What is the minimum signal of use? How to measure it? Initial goal and prod goal?
Layer 2 — Engagement (do they use it properly?):
- What does "use it well" mean? (long sessions, returns, etc.) — metric + goal.
Layer 3 — Value (does it deliver a result?):
- What is the metric that proves ROI to a stakeholder? Baseline and goal?
- This is the decisive metric — it must match a PRD hypothesis. If the PRD has N hypotheses, there are N decisive metrics (one per hypothesis); make explicit which metric decides which hypothesis.
Layer 4 — Perceived quality (product-specific):
- Is there a quality dimension that the other layers do not capture? (E.g., "sounds human", "responds well", etc.) — optional, but valuable for products that depend on experience.
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.
- 1mo ago First seen · 138 lines · 26 tokens per session scan A a80d1df3c4d3
metrics is a command published in the GitHub repository AInsteinsBR/renata (11 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,656 once invoked, about $0.0001 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.
Other commands, from other repositories
pm
PRD generator for AI features. Before an AI feature goes to engineering, lists the decisions still open (failure handling, human review, evaluation), then builds the PRD through 4 gated stages (or a one-shot draft on request) with an AI appendix that turns those decisions into requirements and acceptance criteria.…
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.