A command that combines system discovery and system review into one workflow. It can choose whether to start with a fresh discovery, use existing registry information, or run only one of those stages.

Use it to discover systems, review a selected number of them, filter reviews by subsystem, rebuild discovery data, or run discovery or review alone.

It removes the need to decide manually which discovery and review steps to run. Flags also let you control the scope, number of systems, and whether the command runs without prompts.

make-better — Skill for Claude Code by fivol

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 fivol/claude-make-better --skill make-better

Clone the repo

git clone --depth 1 https://github.com/fivol/claude-make-better

Made for: Claude Code.

Or install make-better, the plugin that ships this one along with the rest of its 4 skills.

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/fivol/claude-make-better/make-better/github.svg)](https://agentmods.dev/skills/fivol/claude-make-better/make-better)

Your own site

<a href="https://agentmods.dev/skills/fivol/claude-make-better/make-better"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/make-better/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fivol/claude-make-better/make-better"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/make-better.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,737 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	$0.00064	$0.01737
Opus 5	$0.00032	$0.00869
Sonnet 5	$0.00013	$0.00347
Haiku 4.5	$0.00006	$0.00174

Measured 8d ago against content hash c2ee35fdb33b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

make-better 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 8d 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/make-better/skills/make-better/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the /make-better orchestrator. Your job is to glue /systems-discover and /systems-review into a single user-facing flow, with smart defaults driven by registry state.

The user invocation is in $ARGUMENTS. Follow this procedure exactly.

Step 1 — Parse $ARGUMENTS

Tokens may appear in any order. Process tokens left-to-right:

--no-discover → set skip_discover = true (run review only)
--rebuild → set force_full_discover = true (force a full re-discovery before review)
--discover-only → set skip_review = true (run discovery only, no review)
--yes / -y / --auto → set non_interactive = true (no prompts, no plan mode — agent runs to completion unattended)
The first remaining numeric token → count (how many systems to review)
All other remaining tokens, joined by space → subsystem filter

Defaults: skip_discover=false, force_full_discover=false, skip_review=false, non_interactive=false, count=null, subsystem=null.

If both --no-discover and --discover-only were passed, stop with: "These flags are mutually exclusive — pick one."

If both --no-discover and --rebuild were passed, stop with: "These flags are mutually exclusive — pick one."

Step 2 — Load configuration

Run the systems-review loader (it exposes the same merged config keys we need):

bash ${CLAUDE_SKILL_DIR}/../systems-review/bin/load-config.sh

The output is a single merged JSON object. From it you need:

registry_path (e.g. docs/SYSTEMS.md)
auto_discover_when_stale_days (default 30)
user_language (for all messages you print)

Render every user-facing message you produce in user_language. Skill instructions, JSON shapes, branch names, commit messages stay English regardless.

Model self-check

This skill is declared with model: opus in its frontmatter, but Claude Code versions that don't honor that field would silently fall back to the user's session model. Verify your own identity before continuing.

Read the full file on GitHub · 136 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.

8d ago First seen · 136 lines · 64 tokens per session scan A c2ee35fdb33b

Subscribe to this mod's changes

make-better is a skill published in the GitHub repository fivol/claude-make-better (5 stars, last pushed 28d ago), licensed MIT. It adds 64 tokens to every session and 1,737 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.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens