prd-evolve

A command workflow for updating an existing product requirements document when the product scope changes. It first compares the change with the current documents and then updates only affected plans and development skills.

In plain words
What is it for?
Use it to evolve a PRD, architecture, data model, and project guidance after a feature, technology, or other scope change.
Why use it?
It avoids losing valid existing decisions or rewriting documents that the change does not affect.

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/rodrigorjsf/prd-generator-plugin/prd-evolve
Clone the repo
git clone --depth 1 https://github.com/rodrigorjsf/prd-generator-plugin
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,757 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 $0.00012 $0.01757
Opus 5 $0.00006 $0.00879
Sonnet 5 $0.00002 $0.00351
Haiku 4.5 $0.00001 $0.00176

Measured yesterday against content hash 40a9ce9c0382, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-evolve 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 yesterday.

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/prd-evolve.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.

/prd-evolve — PRD Evolution

You are orchestrating an incremental PRD evolution. You update ONLY the artifacts impacted by the described scope change, preserving all existing decisions that remain valid.

CRITICAL RULES:

  • All generated/updated files MUST remain in English
  • Do NOT regenerate artifacts that are unaffected by the change
  • Every skill header must be updated with the new prd_version
  • Respond to the user in whatever language they write

Input: $1 — description of what changed (required)


PHASE 0 — Read Current State

Create tasks: Delta Analysis / Research & Validation (if needed) / Artifact Updates / Commit

Pre-flight Check

Before reading any files, verify that docs/prd/PRD.md exists. If it does NOT exist:

  • Error: "No PRD found at docs/prd/PRD.md. Run /prd-new first to generate the initial PRD."
  • Exit without modifying any files.

Read the following files:

  • docs/prd/PRD.md — extract current version from header
  • docs/prd/ARCHITECTURE.md
  • docs/prd/ER.md (if exists)
  • .claude/skills/project-guardian/SKILL.md — read prd_version field
  • .claude/skills/project-architecture/SKILL.md
  • .claude/skills/project-domain-rules/SKILL.md
  • .claude/skills/project-compliance/SKILL.md
  • .claude/skills/project-cicd/SKILL.md (if exists) — read vcs and pipeline_file from frontmatter
  • Identify existing pipeline file: check for .github/workflows/ci.yml, .gitlab-ci.yml, bitbucket-pipelines.yml

Check for stale skills: if any skill's prd_version < PRD's current version, warn the user that skills were already out of sync before this evolution.


PHASE 1 — Delta Analysis

Mark task "Delta Analysis" as in_progress.

Dispatch requirements-analyst agent with:

{
  "mode": "delta",
  "change_description": "$1",
  "current_prd_summary": "<key sections from PRD.md>",
  "current_architecture_summary": "<stack table + ADRs from ARCHITECTURE.md>"
}

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. yesterday First seen · 208 lines · 12 tokens per session scan A 40a9ce9c0382

Subscribe to this mod's changes

prd-evolve is a command published in the GitHub repository rodrigorjsf/prd-generator-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,757 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.