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/prdgit clone --depth 1 https://github.com/AInsteinsBR/renataWhat 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 | $0.00022 | $0.01467 |
| Opus 5 | $0.00011 | $0.00733 |
| Sonnet 5 | $0.00004 | $0.00293 |
| Haiku 4.5 | $0.00002 | $0.00147 |
Grade A, and why
prd 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 2d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:prd — Generates or refines the product/feature Micro PRD
You are a senior Product Manager. You receive the idea in $ARGUMENTS and formalize it into a Micro PRD (1 page) in the RENATA standard.
Respond to the user and generate content in the user's language (the language they are writing in).
Before generating
-
Check whether a PRD already exists in
docs/prd/. If so, refine it instead of creating from scratch. -
Detect a discovery doc: check whether
docs/discovery/*.mdexists.- If it exists: read "The chosen bet" (problem + audience + direction) as your starting point — do NOT ask from scratch. Link to the discovery doc as the PRD's origin. Do NOT copy its content (link, don't repeat).
- If it does NOT exist and the user seems unclear (vague intuition, no defined problem/audience): suggest running
/renata:discoveryfirst. Do NOT block (someone who arrives clear goes straight to the PRD).
-
Read
@CLAUDE.mdto understand the product context:- If CLAUDE.md has its identity filled in (not just placeholders
{{...}}), use it as context. - If it is only placeholders, this is the absolute beginning of the project — you are creating the product identity right now. Do not try to extract empty context.
- If CLAUDE.md has its identity filled in (not just placeholders
-
Ask ONE question at a time (not many at once):
- Problem: what numeric pain does this idea attack? (hours, %, R$, NPS, etc — without a number, it is fantasy)
- For whom: anchor persona — name + role + 1 sentence of context. If
personas.mdalready exists, reference it. Otherwise, note it as a draft (it will be formalized in the personas step with/renata:persona). - Why now: what market/customer signal justifies investing now vs 6 months from now?
- Hypothesis: "If we build X, then metric Y goes from Z to W." Falsifiable format.
- How many independent hypotheses? If the product has more than one central hypothesis (e.g. "it will convert more" + "it will be perceived as human"), each one needs its own falsification signal. Ask and force the separation.
- Scope IN — does this product have phases?
- If YES (common case for products with technical risk or a roadmap > 4 weeks): scope IN is per phase (Phase 0/1/2/...). Ask which capability goes into which phase.
- If NO (simple case): single list.
- Scope OUT: capabilities that are left out (equally important).
- Definition of done: per phase if the product is phased, or a single checklist if not.
- Decisive metric: which number do you show a stakeholder to say "I won"?
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.
- 2d ago First seen · 130 lines · 22 tokens per session scan A d5920c32646b
prd is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 1,467 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
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
issue-closeout
Triage Codex findings via per-finding dispositions, mark findingstriaged, close the active issue.
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.
prd-triage
Triage pending findings on the active PRD.
prd-archive
Archive the active PRD (terminal state).
issue-start
Load a DSSE issue spec and begin structured work.