refine

refine is a command for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 12 tokens per session (552 once invoked), scanned A, original, Apache-2.0.

A command for improving an existing product requirements document through focused questions about selected sections.

In plain words
What is it for?
Use it to revise requirements, architecture, risks, acceptance criteria, scope, or other parts of a PRD.
Why use it?
It helps uncover missing details or update requirements without repeating the entire planning process.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the pwdev-prd plugin — 4 commands shipped together

Good fit Use it to revise requirements, architecture, risks, acceptance criteria, scope, or other parts of a PRD.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace
Claude Code
/plugin install pwdev-prd

Made for: Claude Code.

Or install pwdev-prd, the plugin that ships this one along with the rest of its 4 commands.

Wrote 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.

agentmods badge for refine

README.md
[![agentmods](https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/refine/github.svg)](https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/refine)
Your own site
<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/refine"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/refine/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for refine

Your own site · 80×15
<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/refine"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.00552
Opus 5 $0.00006 $0.00276
Sonnet 5 $0.00002 $0.00110
Haiku 4.5 $0.00001 $0.00055

Measured 5d ago against content hash c2ef3929a79a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

refine 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.

plugins/pwdev-prd/commands/refine.md · 84 lines

What it actually says

/pwdev-prd:refine — Refine Existing PRD

Method (inline — you run in the MAIN context)

You are the PRD interviewer. Follow ${CLAUDE_PLUGIN_ROOT}/references/interview-method.md (persona, principles, consistency checks). No Task tool, no model resolution — you interview the human.

Input

$ARGUMENTS: PRD slug (required).

Flow

STEP 0 — Language

Follow ${CLAUDE_PLUGIN_ROOT}/references/language.md (resolve lang from .planning/config.json; ask only if unset).

STEP 1 — Load existing PRD

PRD_DIR=".planning/prds/$ARGUMENTS"
if [ ! -f "$PRD_DIR/PRD.md" ]; then
  echo "PRD_NOT_FOUND"
  ls .planning/prds/ 2>/dev/null
else
  cat "$PRD_DIR/PRD.md"
fi

If PRD_NOT_FOUND → show the available slugs and STOP.

STEP 2 — Ask what to refine

I've loaded the PRD for "{slug}".

What would you like to refine?
1. Add or modify functional requirements
2. Update non-functional requirements
3. Revise architecture and approach
4. Add or update risks
5. Refine acceptance criteria
6. Update scope
7. Other (describe what you want to change)

STEP 3 — Targeted Interview

Run only the relevant interview steps for the selected sections. Follow the same rules: one question at a time, summarize, confirm.

STEP 4 — Re-run Consistency Checks

Validate the entire PRD after changes.

STEP 5 — Update PRD.md

Rewrite the complete PRD.md with the changes incorporated. If prd.json exists, update it too (canonical structure in ${CLAUDE_PLUGIN_ROOT}/references/interview-method.md). Log: "${CLAUDE_PLUGIN_ROOT}/scripts/audit-log.sh" event refine "" completed ".planning/prds/{slug}/PRD.md" ""

STEP 6 — Ask about commit

If changes were made:

PRD updated. Commit changes? (y/n)

If yes:

git add .planning/prds/{slug}/
git commit -m "docs(prd): update PRD for {slug}"

Prohibitions

  • NEVER lose existing content when refining
  • NEVER skip consistency checks after changes
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. 5d ago First seen · 84 lines · 12 tokens per session scan A c2ef3929a79a

Subscribe to this mod's changes

refine is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 12 tokens to every session and 552 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 2026-09-03.