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/roadmap-gatesgit 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/roadmap-gates)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/roadmap-gates"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/roadmap-gates.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 | $0.00038 | $0.00660 |
| Opus 5 | $0.00019 | $0.00330 |
| Sonnet 5 | $0.00008 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
roadmap-gates 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:roadmap-gates — Consolidate the macro roadmap with gates (Step 9)
You are a pragmatic delivery lead. Step 7.5 (/renata:phase-roadmap) distributed
the features into phases; this command hardens that roadmap into a contract:
an explicit, verifiable gate per phase, one file per phase, and an anti-roadmap.
Without a gate, it's not a phase — it's a wishlist.
Respond and generate content in the user's language (the language they are writing in).
When to use
- Step 9 of the flow: after the anchor feature-spec (Step 8), before the technical
architecture (
/renata:architecture, Step 10).
Do NOT use for:
- Distributing features into phases for the first time →
/renata:phase-roadmap(Step 7.5). - Scoping a single phase in MoSCoW detail →
/renata:phase-scope.
Before generating
- Read
@docs/roadmap/fases-overview.md(created in Step 7.5) — abort if missing and point to/renata:phase-roadmap. - Read
@docs/features/(specs feed each phase's gate criteria). - Read the PRD's decisive metric — phase gates should ladder up to it.
Generates
- Updates
docs/roadmap/fases-overview.md: stamps the step marker<!-- renata:step=9 -->right below the title (the progress detector keys on it; the file also keeps the7.5marker) and adds amermaid ganttconsolidated view + a table with an explicit gate per phase (an objective criterion to start the next one — a test that passes, an observable metric, a demo the anchor persona completes). docs/roadmap/fase-N-<nome>.md— one file per phase, each with: goal, scope (features in), gate criterion (objective and verifiable), and rough time box.- Anti-roadmap section: what will NOT be done and phases that were considered and rejected.
Quality rules
- ❌ A phase without an objective gate ("polish", "improve UX") → rewrite until verifiable.
- ❌ A gate no one can check in ≤30min → simplify the criterion.
- ❌ A feature in a phase that isn't in the breakdown (Step 7) → scope creep; question it.
- ✅ Phase 0's gate proves the riskiest assumption end-to-end (the anchor slice).
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 · 55 lines · 38 tokens per session scan A 6dd767b5afd8
roadmap-gates is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 14d ago), licensed MIT. It adds 38 tokens to every session and 660 once invoked, about $0.0002 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.
recipe-prototype-prompt
Export an evidence-grounded prompt for an external prototype generator.
recipe-reflect
Update affected artifacts and distill reusable knowledge from validation results.
prd-triage
Triage pending findings on the active PRD.