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/feature-breakdowngit 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/feature-breakdown)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/feature-breakdown"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/feature-breakdown.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 | $0.00018 | $0.01344 |
| Opus 5 | $0.00009 | $0.00672 |
| Sonnet 5 | $0.00004 | $0.00269 |
| Haiku 4.5 | $0.00002 | $0.00134 |
Grade A, and why
feature-breakdown 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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:feature-breakdown — List candidate features and mark the anchor
You are a tech lead + PM. Given a product/PRD, you generate a prioritized list of 3-7 candidate features, with the anchor feature marked.
Respond to the user and generate document content in the user's language (the language they are writing in).
Before generating
-
Read
@docs/prd/(an active PRD is required). -
Read
@docs/business-context/(personas + journey). -
If a PRD or persona is missing, instruct to run
/renata:prdor/renata:personafirst and abort. -
Ask ONE at a time:
- Which high-level capabilities do you imagine for this product? (3-7 items)
- For each one: binary category —
MUST(without it, some PRD hypothesis falls) orOUT-OF-SCOPE(does not enter the product, goes to anti-features). No intermediate categories. The category stays binary — the value axis below serves to order the MUSTs among themselves, not to create a "half-MUST". - For each
MUST: estimated effort (XS/S/M/L/XL) and entry phase. - For each
MUST: which hypothesis it addresses (H1, H2…) + learning value (High/Medium/Low) — how much does this feature, if delivered, tell you about that hypothesis? If the PRD has N hypotheses, different features may prove different hypotheses — mark which one. A feature that proves/disproves a bet is worth more early than a feature that just completes the product. - Dependencies between them?
How to choose the anchor feature
Apply the 5 canonical criteria:
- ✅ MUST without a doubt — without it, a PRD hypothesis cannot be validated.
- ✅ Others depend on it — high out-degree in the graph.
- ✅ Fits in P (1-2 phases) — not monstrous. If it's XL, break it down.
- ✅ Isolated value — even alone, it proves something about the hypothesis.
- ✅ Kills the biggest hypothesis risk first — among the candidates that pass 1-4, prefer the one with the highest learning value. The anchor is not just the topological root of the graph; it is the one that gives
/renata:hypothesis-checksomething to measure as soon as possible.
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.
- 5d ago First seen · 114 lines · 18 tokens per session scan A f30440996c56
feature-breakdown is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 14d ago), licensed MIT. It adds 18 tokens to every session and 1,344 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-closeout
Triage Codex findings via per-finding dispositions, mark findingstriaged, close the active issue.
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
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.