plan-phase

A command for turning a feature or roadmap phase into a detailed execution plan. It checks the surrounding project documents, accepted ADRs (architecture decision records), feature specification, and definition of done before requesting architect review.

In plain words
What is it for?
Use it before starting a roadmap phase or planning a feature that needs several implementation tasks. It is not intended for a single architecture decision, a feature specification, or a technical investigation.
Why use it?
It prevents implementation plans from ignoring earlier decisions or missing required context. It also makes completion criteria and review part of the planning process.

Command

Install

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.

agentmods
npx agentmods add commands/ainsteinsbr/renata/plan-phase
Clone the repo
git clone --depth 1 https://github.com/AInsteinsBR/renata
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.02638
Opus 5 $0.00015 $0.01319
Sonnet 5 $0.00006 $0.00528
Haiku 4.5 $0.00003 $0.00264

Measured 2d ago against content hash d0d647365323, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-phase 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.

commands/plan-phase.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/renata:plan-phase — Generates a detailed execution plan that respects the method

You are a tech lead. You wrap superpowers:writing-plans with RENATA guardrails to ensure the generated plan:

  1. Respects accepted ADRs.
  2. Cites the feature-spec of the active phase.
  3. Has a verifiable definition of done.
  4. Goes through @architect review before being approved.

Respond to the user and generate content in the user's language (the language they are writing in).

Critical difference from invoking superpowers:writing-plans directly: writing-plans on its own does not know our method. This command forces the right context before, during, and after.

When to use

  • Before starting execution of a roadmap phase (Phase 0, Phase 1, etc).
  • Whenever you need to generate a detailed plan for a feature or set of tasks.

DO NOT use for:

  • A one-off structural decision → /renata:adr.
  • A feature spec → /renata:feature-spec.
  • A technical investigation → /renata:spike.

Pre-flight (step 1 — prerequisite validation)

Before invoking writing-plans, you MUST validate the 11 prerequisites below, listing the result of each one for the user. If any fail, abort and instruct the user to fix it.

# Prerequisite How to validate
0 The superpowers plugin is installed (external dependency) The superpowers:writing-plans skill is available in this session (it appears in the skill list / responds to invocation)
1 CLAUDE.md exists and has its identity filled in Read the file, confirm that the {{...}} in Section 1 are filled in
2 PRD exists in docs/prd/ ls docs/prd/*.md returns ≥1 file
3 ≥1 structured persona exists ls docs/business-context/personas.md
4 Metrics defined (Layers 1-3 at minimum) cat docs/business-context/metricas.md
5 There is ≥1 accepted ADR in docs/decisions/ grep -l "Status:.*accepted" docs/decisions/ADR-*.md returns ≥1
6 The anchor feature has a spec in docs/features/ docs/features/F1-*.md or equivalent exists
7 The active phase has a file in docs/roadmap/ docs/roadmap/fase-N-*.md for the phase to plan exists
8 .claude/rules.yaml exists and is valid bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/rules-violation.sh" runs without a fatal error
9 There is no overlapping prior plan still active docs/superpowers/plans/ has no running plan for the same phase
10 If the phase has UI capability: design exists in docs/design/ If the phase feature-spec mentions screens/UI but docs/design/inventory.md does not exist → abort and suggest /renata:screens

Read the full file on GitHub · 208 lines

Changes

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.

  1. 2d ago First seen · 208 lines · 30 tokens per session scan A d0d647365323

Subscribe to this mod's changes

plan-phase is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 11d ago), licensed MIT. It adds 30 tokens to every session and 2,638 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.