discover

discover is a skill for Claude Code from bromso/metapowers. It costs 12 tokens per session (448 once invoked), scanned A, original, MIT.

The first research phase of a brand-development process. It gathers information about a business, its audience, competitors, existing brand materials, and goals.

In plain words
What is it for?
Use it to ask discovery questions, review existing assets, research competitors, study the target audience, and document market opportunities.
Why use it?
It replaces guesswork with organized information before creating a brand strategy or visual identity.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the branding plugin — 5 skills shipped together

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 skills/bromso/metapowers/discover
Any agent
npx skills add bromso/metapowers --skill discover
Clone the repo
git clone --depth 1 https://github.com/bromso/metapowers

Made for: Claude Code.

Or install branding, the plugin that ships this one along with the rest of its 5 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.

agentmods badge for discover

README.md
[![agentmods](https://agentmods.dev/badge/skills/bromso/metapowers/discover.svg)](https://agentmods.dev/skills/bromso/metapowers/discover)
Your own site
<a href="https://agentmods.dev/skills/bromso/metapowers/discover"><img src="https://agentmods.dev/badge/skills/bromso/metapowers/discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 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. 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 5.1 $0.00012 $0.00448
Opus 5 $0.00006 $0.00224
Sonnet 5 $0.00002 $0.00090
Haiku 4.5 $0.00001 $0.00045

Measured 5d ago against content hash 58107de571fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

discover 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/branding/skills/discover/SKILL.md · 51 lines

What it actually says

Discover

Research the brand landscape for "$ARGUMENTS". Gather insights about the business, audience, competitors, and market to inform brand strategy.

Prerequisites

None — this is the first phase.

Process

  1. Ask the user key discovery questions:

    • What does the business do? What problem does it solve?
    • Who is the target audience? (demographics, psychographics)
    • Who are the main competitors?
    • What makes this business different?
    • Are there existing brand elements to audit? (logo, colors, messaging)
    • What is the brand's aspiration? Where should it be in 3-5 years?
  2. If existing brand assets exist:

    • Ask the user to place assets in .metapowers/branding/$ARGUMENTS/assets/ (logo/, fonts/, imagery/)
    • Review and document what exists
    • Assess current brand strengths and weaknesses
  3. Competitive brand analysis:

    • Use WebSearch to research competitor brands
    • Document their positioning, visual identity, and messaging
    • Identify gaps and opportunities for differentiation
  4. Audience research:

    • Use WebSearch to understand the target audience's preferences, behaviors, and expectations
    • Document audience personas with needs and pain points
  5. Write the artifact to .metapowers/branding/$ARGUMENTS/01-discover.md with sections:

    • Business Overview — what the business does, its goals
    • Existing Brand Audit — current assets, strengths, weaknesses (if applicable)
    • Competitive Landscape — competitor brand analysis
    • Target Audience — personas, needs, expectations
    • Market Insights — trends, opportunities, gaps
    • Key Takeaways — most important findings for the Strategy phase

Output

The discovery brief written to .metapowers/branding/$ARGUMENTS/01-discover.md. Present a summary to the user highlighting:

  • Key audience insights
  • Competitive positioning gaps
  • Biggest brand opportunity identified
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 · 51 lines · 12 tokens per session scan A 58107de571fd

Subscribe to this mod's changes

discover is a skill published in the GitHub repository bromso/metapowers (1 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 448 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.