pluxx-refine-plugin

pluxx-refine-plugin is a skill for Claude Code, Codex from orchidautomation/pluxx. It costs 25 tokens per session (448 once invoked), scanned A, original, MIT.

A coordinated workflow for improving a Pluxx plugin after its initial scaffold has been created. A scaffold is the generated starting structure of a plugin.

In plain words
What is it for?
Use it to prepare context, refine skills, rewrite instructions, review the scaffold, and run Pluxx validation commands.
Why use it?
It addresses weak grouping, generic instructions, missing product context, and confusion between coding-agent hosts. It brings these improvements together in one review pass.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare context, refine skills, rewrite instructions, review the scaffold, and run Pluxx validation commands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orchidautomation/pluxx/pluxx-refine-plugin
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 orchidautomation/pluxx --skill pluxx-refine-plugin
Clone the repo
git clone --depth 1 https://github.com/orchidautomation/pluxx

Made for: Claude Code, Codex.

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 pluxx-refine-plugin

README.md
[![agentmods](https://agentmods.dev/badge/skills/orchidautomation/pluxx/pluxx-refine-plugin/github.svg)](https://agentmods.dev/skills/orchidautomation/pluxx/pluxx-refine-plugin)
Your own site
<a href="https://agentmods.dev/skills/orchidautomation/pluxx/pluxx-refine-plugin"><img src="https://agentmods.dev/badge/skills/orchidautomation/pluxx/pluxx-refine-plugin/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 pluxx-refine-plugin

Your own site · 80×15
<a href="https://agentmods.dev/skills/orchidautomation/pluxx/pluxx-refine-plugin"><img src="https://agentmods.dev/badge/skills/orchidautomation/pluxx/pluxx-refine-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 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 $0.00025 $0.00448
Opus 5.5 $0.00010 $0.00179
Sonnet 5.5 $0.00005 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 2mo ago against content hash b9dbc829b9a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pluxx-refine-plugin 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 2mo 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.

example/pluxx/skills/pluxx-refine-plugin/SKILL.md · 58 lines

What it actually says

Pluxx Refine Plugin

Use this skill when the first scaffold exists, but it still feels too lexical, too generic, or too weak to ship as a serious plugin source.

This workflow intentionally bundles several internal stages that advanced operators may think of separately:

  • context preparation
  • taxonomy shaping
  • instruction rewriting
  • findings-first scaffold review
  • host-translation review when that is the real blocker

Workflow

  1. Identify the real refinement target:
    • missing product context
    • weak taxonomy
    • generic instructions
    • host-translation confusion
    • broad scaffold quality concerns
  2. If context is weak, prepare it first:
    • pluxx agent prepare --website ... --docs ...
  3. Tighten the scaffold as one coordinated refinement pass instead of several disconnected edits.
  4. Use the granular workflows only when they materially sharpen the pass:
    • pluxx-prepare-context
    • pluxx-refine-taxonomy
    • pluxx-rewrite-instructions
    • pluxx-review-scaffold
  5. Re-run the smallest useful structural checks:
    • pluxx lint
    • pluxx eval
    • pluxx test
  6. Return:
    • what changed
    • what stayed intentionally unchanged
    • what still needs proof rather than more copywriting

Rules

  • Keep the visible user job simple: “make this plugin feel real,” not “pick one of four adjacent micro-workflows.”
  • Group recommendations by user job and host reality, not by file names alone.
  • Do not pretend host parity where translation or degradation is the honest answer.
  • If the scaffold already reads well, do not churn wording just to look busy.

Output

  • Explain the refinement pass in workflow terms, not as a file-by-file changelog.
  • Call out the core-four translation story when it matters.
  • Make the next step obvious:
    • prove it
    • sync later
    • or publish
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. 2mo ago First seen · 58 lines · 25 tokens per session scan A b9dbc829b9a3

Subscribe to this mod's changes

pluxx-refine-plugin is a skill published in the GitHub repository orchidautomation/pluxx (5 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 448 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

pluxx-refine-plugin compared with skills from other repositories

pluxx-refine-plugin next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pluxx-refine-pluginorchidautomation/pluxxSkill51mo agoMITA25Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code