What is refinement-review?

A review of a draft user story by three roles: a product owner, a software architect, and a user-experience specialist. It combines their feedback into a readiness decision before implementation.

Use it to review a story written in text, stored in a file, or referenced by an issue number before planning the implementation.

It exposes unclear scope, design concerns, and user-fit problems while the story is still easy to change.

refinement-review — Skill for Claude Code by cpliakas

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.

Any agent

npx skills add cpliakas/claude-code-engineering-leaders --skill refinement-review

Clone the repo

git clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leaders

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/refinement-review.svg)](https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/refinement-review)

Your own site

<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/refinement-review"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/refinement-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,072 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.02072
Opus 5	$0.00031	$0.01036
Sonnet 5	$0.00012	$0.00414
Haiku 4.5	$0.00006	$0.00207

Measured 7d ago against content hash ea6318436155, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

refinement-review 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 7d 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.

skills/refinement-review/SKILL.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convene the Product Owner, Chief Architect, and UX Strategist in parallel on a story draft. Each peer reviews the story from their own perspective and returns an explicit verdict. The skill assembles a consolidated report with an overall readiness verdict (ready / needs-revision / blocked), named peer accountability, verbatim peer input, and next steps.

This skill is complementary to /refine-story (INVEST structural scoring) and /write-story (story authoring). Use /refinement-review when the story draft exists and you want strategic sign-off before implementation begins. Run /plan-implementation after /refinement-review returns ready.

Accepted Input Forms

$ARGUMENTS accepts three forms:

Inline story body: paste the full story or issue description directly as the argument. The skill uses it verbatim.
File path: a path to a markdown file containing the story or issue body (e.g., ./stories/auth-feature.md or /path/to/story.md). The skill reads the file and uses its contents.
Issue reference: an issue identifier (e.g., ENG-123, #42, beads-456). The skill attempts to resolve it via the configured issue tracker CLI (e.g., bd show <id>, gh issue view <id>). If no CLI is available or the reference cannot be resolved, the skill prompts for the story body before proceeding.

Step 1: Resolve Input

If $ARGUMENTS is empty, prompt the user:

Please provide the story draft to review. You can paste the story body directly, provide a file path (e.g., ./story.md), or provide an issue reference (e.g., ENG-123). Do not proceed until a story is provided.

Do not guess. Do not continue with a placeholder or fabricated story.

Once $ARGUMENTS is provided or confirmed:

If it looks like a file path (starts with /, ./, or ../): use the Read tool to load the file. If the file does not exist, report the error and prompt for the story body directly.
If it looks like an issue reference (the entire trimmed value matches patterns like [A-Z]+-\d+, #\d+, or beads-\d+): attempt to resolve via a configured CLI. Try bd show $ARGUMENTS first; if unavailable, try gh issue view $ARGUMENTS. If the command exits non-zero, is not found, or returns empty output, surface the failure and prompt for the story body directly:
```
[INPUT ERROR] Could not resolve `[issue reference]` (tried: `[command]`).
Please paste the story body directly.
```
Otherwise: treat $ARGUMENTS as the inline story body.

Read the full file on GitHub · 256 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

7d ago First seen · 256 lines · 62 tokens per session scan A ea6318436155

Subscribe to this mod's changes

refinement-review is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 15d ago), licensed MIT. It adds 62 tokens to every session and 2,072 once invoked, about $0.0003 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.

Design and UX Planning

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).