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/phase-roadmapgit 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/phase-roadmap)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/phase-roadmap"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/phase-roadmap.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 | $0.00025 | $0.01224 |
| Opus 5 | $0.00013 | $0.00612 |
| Sonnet 5 | $0.00005 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
phase-roadmap 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:phase-roadmap — Distribute ALL system features into time-based phases
You are a macro-planning tech lead. You receive the complete list of features (from
/renata:feature-breakdown) and distribute them into sequential phases (Phase 0, 1, 2...) with an
approximate time per phase. No feature is left out — what changes is which
phase each one enters. Phase 0 is the anchor set: the minimal vertical slice that already
delivers end-to-end value.
Respond to the user and generate document content in the user's language (the language they are writing in).
Difference from /renata:phase-scope (do not confuse)
/renata:phase-roadmap(this one): macro view — distributes the WHOLE system into phases. Runs ONCE, right after the breakdown. Generatesdocs/roadmap/fases-overview.md./renata:phase-scope <N>: micro view — goes down into a specific phase and applies MoSCoW + budget. Runs per phase, when you are about to execute it.
Pipeline: /renata:feature-breakdown → /renata:phase-roadmap → /renata:phase-scope 0 → /renata:feature-spec (per Phase 0 feature).
When to use
- Right after
/renata:feature-breakdown(Step 7.5), before speccing any feature. - When the set of features changed and the phasing needs to be redone.
Before generating
- Read
@CLAUDE.mdand@docs/prd/(hypothesis + decisive metric). - Read
@docs/features/README.md(ALL features and their dependencies). - Read
@docs/business-context/jornada.md(Phase 0 must close ≥1 anchor journey end-to-end). - Ask ONE at a time:
- How many phases will the system have? (suggest 2-5; more than that is probably a roadmap too long for this round)
- Total available time / horizon? (e.g., "3 months", "1 sprint per phase")
- Which journey must Phase 0 close end-to-end? (defines the anchor set)
- External constraints? (a scheduled demo, a customer dependency, a deadline)
Quality rules
- ❌ A breakdown feature that appears in NO phase → refuse. No orphans.
- ❌ A Phase 0 that does not close a journey end-to-end → it is not an anchor, it is a fragment. Redo it.
- ❌ A phase that depends on a feature from a later phase → invalid order. Reorder by dependency.
- ❌ A phase without an approximate time → require a t-shirt size (XS/S/M/L/XL) or weeks.
- ❌ A Phase 0 bigger than the rest combined → a bloated anchor. Trim it to the minimal 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.
- 3d ago First seen · 113 lines · 25 tokens per session scan A 2962a50c85a4
phase-roadmap is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 12d ago), licensed MIT. It adds 25 tokens to every session and 1,224 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.